Would be nice if they donate to LibreOffice then, to improve the support of various MS Office features in files, as well as comparison/diffing features. Win-win to everyone.
Do you mean that it's good that companies can profit over people's mostly voluntary efforts for free, or Free Software is meant to be used for free and never supported in any way, or what?
They just imply them not having to doesn't dismiss the original comment, thread being more about morals than laws.
That being said, hoping for any financial support from AI companies would be really naive. Using others work without retribution is at the core of their model.
> That being said, hoping for any financial support from AI companies would be really naive. Using others work without retribution is at the core of their model.
I have no such expectations. They believe that they own the world and owe nothing, as you said.
You are allowed (and encouraged) to do good things without being obligated to.
I think it would be immensely cool if OpenAI donated some of that crapload of AI money to the people behind LibreOffice to help with development - and then having like a blog post about it or something would already improve the project's visibility a bit more (hey, every bit helps). What's peanuts to them could help with the sustainability of the project a whole bunch!
> You are allowed (and encouraged) to do good things without being obligated to.
We're absolutely on the same page with you, and I try to do my best with what I can in that regard.
On the other hand, I see a perspective which thinks that companies are entitled to use everything for free and don't need to support the Free Software ecosystem because it's an externality that they don't have to care for, which bothers me a lot.
What I was trying to understand that whether this comment was supporting that perspective, or is there something I'm missing entirely.
You are not allowed to do good things. The penalty is more subtle: instead of cops showing up to arrest you, you will be outcompeted in the market. It's really hard to see when this is happening and course-correct, so all rational actors are doing their utmost to prevent it at all times.
What does donation does for open source? Surely it wont come close to pay talented developers who create it. For cloud cost, there are few companies already giving generous free tier for open source.
The only thing that donation could pay for is marketing e.g. events and meetups.
That's not true at all. Donations are the biggest source of income for The Document Foundation, the non-profit behind LibreOffice, and have been used to pay developers who've joined the team in recent years:
* Michael Weghorn (accessibility)
* Jonathan Clark (language and scripting support)
* Neil Roberts (scripting improvements)
* Dan Williams (macOS support and general UI improvements)
It obviously depends on the project and the scale and duration of a donation, but plenty of open source projects have benefited from donations. Donations can and do pay for developers, as well, part time or full time. With LibreOffice, you can answer your questions directly by browsing https://www.libreoffice.org/donate/ and as a non-profit you can easily find more detailed reports: https://www.documentfoundation.org/financials-and-reports/
I agree that it would be the right thing to do. Which is why you have to make the best attempt to make it the legal thing, because people looking to make money will not care about what's right. So, it makes sense to point out the disconnect when people use and promote pro-corporate licenses and then get upset when corporates follow them to the letter and provide them nothing but demands in return.
If you want a mutually beneficial community, you should contribute and distribute using a license that requires it.
> because people looking to make money will not care about what's right
This is two-sided: making a kind of license mandatory also shrinks adoption if it is more restrictive. So, even if I acknowledge there is truth in your side of the story, there is also another at the other side, as usual.
How many people use GPL-licensed software as opposed to MIT licensed?
That is not the problem of GPL. I'd rather have high quality software with patches shared back and always being able to see the code than some popular software that eventually is used in some corporate environment without the ability see what they changed.
Regardless, who cares about "adoption?" That's not the original point of open source which was that if you're working on something and you wanted to share it, you could, without any expectation of usage, merely that it might help just one extra person out there. It's simply human ego to care about adoption and GitHub usage and stars especially have accelerated this.
> and you wanted to share it, you could, without any expectation of usage, merely that it might help just one extra person out there
Related: how do you think you can attract more people, by setting a restrictive copyleft that some people will use in their spare time or by attracting even corporations with money that will end up committing to a repo that is used in half of the world?
Note that I am talking about adoption bc thanks to adoption things just do not get rotten. If you make a piece of software and set a license that noone wants to touch, you will see it stall and die in front of your face.
Do not take me wrong, I mean, I think it is fair to contribute back, collaborating, sponsoring and so on. But it is a fact of life that if you make certain choices you make adoption more difficult with all the consequences it entails.
I do know what the original spirit of such licenses is. I was talking about real side-effects these choices have.
Why would I care about attracting more people? Not every piece of software needs a hundred contributors. As long as it works for me and maybe someone else gets use out of it, that's all that's needed in the eyes of the original spirit of the licenses. Stallman just wanted to fix his printer, not continuously work on that code for ten years.
Well this goes into the debate of "is morality absolute or relative" which gets religious fast and there's more books on the subject than we have time to read.
The question of "are laws there to enforce morality, or enforce public order?" is the key one. And, I think, very easily settled by looking at the laws we choose to implement. Almost none of them enforce moral behaviour (e.g. you must give 10% of your income to charity), they're all about enforcing how we interact and how we're ruled.
It's not really that "absolute". Laws are not all made the same. Some start as a reflection of what society considers "right" at the time. Then the laws fall behind as society's morality reaches a tipping point. So the society pulls that part of the legal system behind it. Other laws are progressive, and they pull society's morality behind them. Some are driven by/for the majority, and some by/for the elites.
But they all reflect the morality of society to a degree, whether the democratic majority, or the powerful minority.
It is somewhat interesting that the version of morality an individual possesses always feels to that individual as an absolute.
"Of course it's wrong to beat your wife!" says the person who beats their children in a society that has only recently ceased infantilizing their women (USA circa 1900 +/- 30 years).
"Of course it's wrong to own slaves!" says the person whose society only recently began protesting against and/or illegalizing slavery (USA circa 1866 +/- 10 years)
They say this not knowing that had the event of their births been moved a few decades in the wrong direction their morality would have shifted with it.
Those same people might have said "Of course its wrong to beat your wife with a rod thicker than your thumb!" or "Of course its ok to own slaves as long as you treat them well!" at the same point in their lives had they been born maybe 30-50 years earlier.
We currently eat animals as a normal part of our diet (for most of us, including me, anyway). To do this we treat the animals horribly. Incredibly badly. And we know it.
It's very easy to see how society's morals will probably change on this, in fact are changing on this, and how in 50 years' time our current stance on eating animals could be seen as monstrously immoral and indefensible.
Animals eat each other. Often in ways more "horrible" than what we do to them (in quotes because nothing in nature is horrible. Horror is a human notion).
Animals are not moral agents, and eating them is not different from eating plants. Both are part of the biosphere that we manage to our benefit.
And to complete a particularly cultural PoV, there are many people eating "pet" chickens, "pet" guinea pigs, goats, et al about the world.
Good arguments, particularly in Australia, for eating wild pigs, clean skin bulls, camels, donkeys (mainly for pet meat IMHO), etc. Kangaroos, unculled, explode in number past the sustainability of their landscape and litter the ground with bones - humans estimate a cull target and shoot to reduce populations, only eating a few themselves (leaving many on the ground for "nature").
I'm native, and my ancestors were called "dog soldiers" because we would bring dogs with us to war, and when rations got a little tight we would throw fido into the pot. Eating dog is generally considered abominable when you love them as pets but it's a common thing in many societies and not wrong.
I will say though, I would only ever consider eating a dog in a life or death situation.
If there was no absolute need for me to eat a dog then I would not do it, and even if there were it would be a difficult moral dilemma for me that should I survive could possibly haunt me for life, but for my ancestors it was a common occurrence.
Mostly individuals decide what they will do, and then communities decide if they respect that or not. Doesn't exactly apply to companies tho, since they're functionally sociopaths.
"you people" means people that always mix up the legal thing with the right thing? It's tautological to say they're always doing that because that's how you defined them! Are you trying to say that you've encountered other people doing that before too and you've built up an annoyance with them?
Surely "the right thing to do" includes some element of the authors' explicitly stated preferences about how they wish to be treated.
In this case, they chose -- explicitly -- to NOT require any payment or contribution from anyone.
Your feelings about what constitutes "the right thing to do" are apparently different from those of the authors. You believe you know better than they themselves do how they should be treated.
They clearly would like donations, but choose not to require any payments.
Your line of reasoning seems to be along the lines of "anything not forbidden is compulsory" which is not a good place. Having the choice to donate but not being required to is good.
And yes, I think that if OpenAI is choosing to include an entire copy of LibreOffice in their product, it is definitely the right thing to do to sling them a donation. Note that the moral thing to do is not always the required thing to do, or even the legal thing to do.
More like, don't expect anything if not forced. Most people only generally pay for things if there is no other option. It's about what's moral (even then debatable as everyone has different morals) versus what's realistic to expect.
That article has no detail. How much did they make? They said they hope to break even in 2019 so they weren't profitable, what are the latest stats? Compare this to NYTimes which has been crushing it after implementing their paywalled subscription.
> Surely "the right thing to do" includes some element of the authors' explicitly stated preferences about how they wish to be treated.
It does! And they wish to get donations. There's a button right at the top on the site making that clear.
> In this case, they chose -- explicitly -- to NOT require any payment or contribution from anyone.
Yes, so what? It is true that they wished to not require payment. That is one of their wishes, but they have more than one wish. And if they required payment, that wouldn't be a donation anyway.
I actually bundle LibreOffice with my app too and the reason is reading files, especially old xls files. Since I'm bundling it I'm now using it for everything docs related but the specific reason is those old files. I couldn't find anything else that I could just drop it and feel confident it'll just read anything I give it.
>How much money have you contributed back to this seemingly indispensable project?
Perhaps it's time for you to become familiar with the terms of the Mozilla Public License, under which Libre Office is released. There is no requirement for monetary compensation.
Yeah but like, we don't know if OP is making any money off this, let alone significant money. Let's not instantly hold them to the same "please contribute or you're dragging things down" standard as a zillion dollar corporation.
You believe you know better than the authors themselves about how they ought to be treated?
They chose -- explicitly, voluntarily, knowingly -- to give the thing away for free. That's their right for their own creation. Your preferences don't supersede theirs.
You've emphasized this point more than once, but I don't think it's a good counterargument to the GP. It is equally valid to say that they have explicitly (voluntarily, knowlingly) chosen to accept donations for their work.
By profiting off their work and not supporting them you are making your own choice. It says nothing about the authors' preference.
Does that really mean that it's bundling those apps from the start or did it just download and install them at some point to do some local work on some prompt or job you ask it to?
I don't see it making much sense to bundle it. I'm sure a LOT of LLM prompts are related with docs, excels, powerpoints etc, etc but don't really see it worth it for it to be bundled on the codex app from the get go, because otherwise, why not also install dozens of other apps?
I'm not sure. Someone who hasn't installed the ChatGPT (or Codex) apps yet could confirm this by installing the apps, seeing if that ~/.cache directory exists, then try running a prompt that needs Python or Node.js or LibreOffice and see if it downloads them when needed.
Is this perhaps because the aim is to read Office documents and there are (maybe, I don't know for sure) default components within Windows that can do that?
Notably: this did not exist after I installed the app, it existed after I ran the app and there was the long startup screen. Presumably, and I'm not sure I'm interested enough to redo it all and find out, that long startup screen involves the default skills plugins setting up their environment and one of those pulls it as a general app requirement.
I also saw this present after first run on macOS but not Windows.
The new app is an unbelievable mess. Settings are senselessly organized, too. The whole thing has this aesthetic slickness and then underneath it's like the people who make it have never even used it.
It's not surprising that it's pulled in absolutely massive dependencies, although I'm not sure it's the wrong call on some operating systems. LibreOffice is pretty tried and true.
Personally, I like the 3-pane organization (sidebar, chat, browser). I turned ChatGPT into my bookkeeper and social post writing/kanban space, and it works well for these script+browser workflows on desktop.
However, all of this is confusing:
- the ChatGPT/Codex split on desktop
- Chat/Work split on mobile
- how you remotely access each chat from your phone (some of my most valuable chats are buried in Remote)
- which chats propagate from device to device, and which remain on that device
This is from a recent update, and I'm on macOS. I had to re-download it, not just update from within the app.
This new version has tabs for ChatGPT and Codex. The ChatGPT tab seems way less powerful; Codex is basically a coding agent with a UI and browser built in.
Pretty sure this is the old Codex app with the ChatGPT tab bolted on. It's great in some ways, but needs work in others.
The thing that blows my mind about it is that they straight up copied Claude Code and tried to frame it as some sort of incredible accomplishment. There are no new ideas, no insightful UI/UX paradigms, no killer features. They say money can't buy taste. The ChatGPT/Codex app is proof that it cannot buy creativity either.
They removed the global shortcut to show a portable chat overlay. That one entrypoint must've been the source of at least 80% of my chats, yet apparently it was considered too vestigial to keep.
Where are the AI-will-render-software-engineers-obsolete and/or vibe-coding apologists? They can make all kinds of nice-sounding arguments, but if AI is contributing to a degradation in product quality, their arguments cannot stand up to the reality we see with our own eyes. The proof of the pudding is in the eating, and all that.
It is the same with Claude Code. Pretty much each change Anthropic makes to it now lowers its quality. Just yesterday they auto-updated it, and now backspace in the CLI does not work reliably. It also insert the enter key command when there is a line break in text that you are pasting, causing fragments of the prompt to be sent prematurely. What the heck! And pretty much all the regressions I have experienced this year have also not been fixed.
Istg on windows, I can't get codex app, new chatgpt or chatgpt classic to work without hanging on even a moderately sized chat. I tried all of the different tricks people recommended but that shit just crawls. It was stable at some point, classic that is, but then it started being a laggy mess.
I've uninstalled new chatgpt/codex app. I can't access phone chats on it, I can't use the desktop allocated chat messages on it. I have to use up codex limits. I am so surprised that OpenAI ships that hot garbage on windows.
They're also great at powershell, you just need to tell it to do so. sh is neat but it's 55 years old, there are newer and better shell environment concepts out there and the robots can handle them well too, try it some time!
PowerShell unfortunately just isn't that first-class, even on Windows. You'll inevitably discover, if you do this, that certain things simply can't be automated via PowerShell, that some PowerShell modules wrap or lag behind older Windows CLI tools, that various things you want to do still require manual registry hacks, etc.
Try starting from a blank slate Windows machine and making a commitment to only changing settings via PowerShell, and ideally only declaring them using DSC. You'll soon discover settings where the best you can do is snapshot the registry, change a setting in the GUI, snapshot the registry again, then take a diff so you can write the registry change into your PowerShell automation. If you're on a corporate machine, you'll also likely find many corners of PowerShell that you need closed off to you, anyway.
At the end of the day, Windows is not friendly to automation because it's not CLI-first (not culturally and not technically).
Your argument is directed at Windows, not PowerShell. The shell is just a shell, if a certain thing you're looking to configure doesn't have an easy cmdlet, that doesn't mean powershell is bad, just that MS didn't give you the easy button. Similar to many unix tools, some of what you need to interact with has a dedicated CLI, other things have you poking at the configuration database directly (ini or yaml or whatever for unix, registry for windows).
If you don't like the Windows style of configuration, run powershell on linux - it's awesome there too!
I'm not sure why reading and writing the registry is considered a bad interface for programmatic system administration.
I realize text files can be processed by utilities for working with text files. And text files can be read by humans without any tools, and in that sense are rather universal.
I wonder what I'm missing.
I'd go so far as to think an OS that had a database at its core, or perhaps a persistent lisp would be even more programmable and legible.
Maybe better tools for dealing with structured data would help this?
That’s easy: you activate WSL and then ask the LLM how to get networking and stuff working since they changed it with WSL2. You need a config file flag to setup network mirroring now.
Kind of, Swappa has new sealed units with the original warranty (and the warranty timer only starts when you set up the device), but indeed these are resale and not directly from Apple.
Do you have any tips for running Codex on the Macbook Neo? Have you changed any setting? On mine, it stutters on every single chat, and I don't even have any plugins installed.
Are you on the recent update that handles long chat sessions much better? That made a big difference. Biasing towards lightweight and fast tool alternatives (uv over pip, bun over npm, ripgrep over grep, etc).
If that still doesn't resolve it, a free tier VM might be the move. I suspect OpenAI will be bundling some kind of VM with their new Astra release, which Sama said yesterday will be released soon (this week maybe?). If this new model supports much longer running tasks, you'll want a dedicated box that can run 24/7 even when your Neo is closed and asleep anyway.
One thing I've found - these things are pretty good at troubleshooting desktop problems. If the codex app is running slow, I'll note that it shouldn't be, and also you might get more traction than you'd expect asking the codex app why it's slow.
How so? On Windows, I like it (version 26.825.51511).
Works fast (like modern Claude Code desktop, their old versions were bad), has pretty okay UI (could have an option for wider main text display, like ZCode added), allows you to change the fonts and shells and some of the layout stuff.
I mean currently I have Paseo hooked up to OpenCode that runs the actual models and often that works a bit better for me, but as a standalone desktop offering, the ChatGPT app has been okay in my experience. I can kinda see why ZCode copied them a bunch (though ZCode also lets you run 3rd party models, which is actually preferable to me).
I do like the idea that Claude Code desktop had in the earlier versions, 3 tabs - chat, work, code, except they kinda went in the direction of merging chat and work which was very ehhhh. The ChatGPT app doesn't even have a proper split between chat and work/code.
Is that what it is using to render and manipulate MS Office documents? That'd explain the poor rendering of some of my files. Bundling all of LibreOffice seems like a pretty huge dependency.
What's ironic about this is, afaik there's no programmatic way to get a screenshot of a PowerPoint on windows other than opening up PowerPoint and screenshotting it. I only discovered this when I first tried out Anthropics official PowerPoint skill when it came out this winter.
If anything happens from this, I hope it forces Microsoft to address some of its long standing hostile to power users issues so they can stay relevant in the world of AI tooling.
This can absolutely be done programmatically. I just added the ability to do that using PowerPoint for Windows yesterday in my uv/python tool `markdown-pptx`. Codex added the functionality in less than 5 minutes.
For those that are interested, this inspired me to create a tool just for exporting images and PDFs of Word, Excel, and PowerPoint files. Check out the repo below, or if you have uv installed just run `uvx office-export skill install` or `uvx office-export --help` to check it out.
It uses Office for Windows, so it is Windows only. I don't currently have access to a Mac machine, so I can't build in Mac support yet.
Thanks for sharing, now im wondering if they did in fact grant my wish since I messed with this in January. Im lucky my job does not require me to make any pptx presentations.
Cool project! I'm playing around with some similar stuff, but via uv/Python. Impressive you aren't leveraging any other existing libraries for OpenXML parsing, editing, or rendering. Any especially tricky gotchas you've run into for this tool?
Yeah thanks to LLM hill climbing and PPTs being easily available and they being nothing more than just xmls this did not involve any gotchas, just a about a weeks worth of goal chasing with manual verification. I did have to stop LLM into hardcoding a lot of times trying to escape the actual goal.
But based on this I thought I could make something similar for cad files, and they turned out to be an entirely different monster. the cad spec is like 1000x bigger than ppts, cad files themselves were hard to gather for test targets. 70-80% of their spec is public and remaining is driven by private vendors. the format itself is in binary. The LLM has been chasing that goal since about 2 months now and its nowhere close.
I have a skill that instructs ChatGPT/Codex to verify the rendering using the Mac versions of Microsoft Office. Even without registering, you still can open files read-only, which is enough. Apparently Office refuses to open some Open Office XML documents that LibreOffice is fine with, so that's another reason to use this. After a few times, Codex ended up storing some memories to stop producing broken files in the first place.
For a docker image of mine I was bundling the full version of LibreOffice as well but I managed to get some space savings by bundling just the no-gui version.
If you've ever actually gone down this route you will try exactly this realize how much of a cluster f these products are and just use libre.
I did the exact same thing in my AI system. Spent an ENOURMOUS amount of time trying everything I could and in the end libre was the only thing even somewhat functional.
Easily 2 months of my life lost to these god forsaken systems. APIs and CLIs sound reasonable until you actually attempt anything in this space.
Computer use is exactly the same thing. Go try this: go to a google doc and dev tools check out the dom and now do the same for a word doc. Eye gouging pain of trying to get anything to work.
Computer use is slow and can take control of the application focus. I’ll be doing things while Claude runs in the background. Suddenly it decides to open the app and try to do something + screenshot it.
I don't know how many times I've had to yell at codex or claude to use/implement headless versions of whatever it's doing at the time, interrupts me trying to multitask and play Battlefield or Factorio while they work :P
don't try Dyson sphere project (/s, its acrually really great), but maybe try x4 foundations, I'm contemplating how I might have my agent help manage my empire
I don't think that's anywhere near equivalent. That's for reading and writing Microsoft Office docs. It has no office functionality. LibreOffice has a full API, for example to run calculations on spreadsheets [1].
The goal of bringing in dependencies is so you don't have to duplicate the functionality, in this case, crafted over decades of effort.
There is a serious threat to Microsoft here, if everyone starts using AI for generating and updating Office docs. At some point Office will become just a viewer.
im stoked for that outcome, standard document tooling should not live behind subscription models anymore. i dont care that microsoft spent zillions bankrolling education systems and companies to fall into this cultural lock in over the decades
whether they like it or not spreadsheets word docs etc are just ubiquitous parts of existing in society at this point you're gonna need to reach for these tools eventually just to apply for jobs or do homework
You assume tokens will be free after these get their monopoly positions? Actual libre office is actual open source running on weak hardware. Truly free.
And I suspect we will look back at MS with nostalgia once Altman and Musk get their ai imperiums.
Satya said some time ago that they expect soon to have more agents using Microsoft software than humans, and are working on transitioning their focus from serving humans to serving agents.
So they will switch to per-agent pricing instead of per-user. Fine, but that doesn't change the fact that Microsoft Office will become a just bunch of viewers as far as human usage is concerned. As far as generating Office documents, you can do that without using any Microsoft code.
This is one that's already true and "everyone" hasn't figured it out yet. But you don't really even need Office as a viewer, PDF is fine (for printable/portable fixed-layout) or just HTML. "Office" is a product that doesn't need to exist anymore, at least for the core apps. For day-to-day office work, you probably shouldn't be using those legacy apps, you should be reviewing portable document formats and asking an agent to make the revisions that you want.
> For Microsoft, this shift means products like M365 will act as the foundational layer where AI agents operate. Users will still need places to store documents, manage projects, search files, and track workflows
This sentiment is also why Microsoft crushed earnings this quarter. Their AI play is to create corpo-slop AI middleware, which sits between AI models and enterprise applications. Sure, others can go and build harnesses which can generate MS office documents, but MS is already doing it, and conveniently such harnesses will come with everyone's existing Microsoft 365 subscription.
The analogy is IBM. Just like IBM helped every old-money corporation on the planet figure out the whole "computers" thing 50 years ago, MS will help everyone solve the "AI" thing. The software will suck and will not really innovate, but it will make a ton of money
> The software will suck and will not really innovate, but it will make a ton of money
Microsoft’s goal isn’t to provide high quality software that outperforms other software, their goal is to provide an obvious and reasonably proximate answer to clueless execs trying to check things off of a procurement list so that existing contracts can snowball and competition is excluded.
We, collectively as a global species, really lost out when MS wasn’t divvied up in their anti-trust trial. Office as its own corporate entity would be in a radically different place right now, as would their enterprise customers.
I have not created or read any Word document for a very long time. I only create PowerPoint presentations a few times a year for work, which could be easily replaced with PowerPoint online or Google Slides or even just some markdown files.
But I have a license for the entire office 365 including Copilot premium.
If you don't have to edit files or you are not supposed to, they should send you a PDF, unless it's an Excel. Excel is a much better viewer for itself because of many reasons (explore the formula, sort, filter) including that usually its sheets are not built to fit a particular page format.
Despite the title, I'm not sure it's actually bundled. Some of the skills plugins will download it on the first run. So it depends where they are grabbing it from rather than the presence of the binary on the system, but I haven't checked that deep into where they actually grab it.
The license itself may be present in the cache folder.
Alternatively, ChatGPT might happily disclose authorship and licensing if asked.
I'm not convinced of the argument that the fact that it is not bundled at download or even at install-time, would free them of the GPL responsibilities. And at this point.
I'm also not sure HOW the devs bundled libreoffice, whether they just mentioned in a prompt (use libreoffice), or whether they hardcoded a command (like apt install libreoffice), more likely the former, considering the recursive vibecoding nature of this software.
Whole lotta words to say that I don't know whether this is a GPL violation, but interested in the answer. If it is a violation, the likely fix will probably be yet another prompt that says something like "comply with licensing", which probably already exists, so a more specific "provide attribution (in a way that doesn't bother the user)"
Now someone please use ChatGPT/Codex or Claude Code to rewrite the entire LibreOffice source into a single Rust binary already! Just like Jarred Sumner did for Bun [1] or Carmine Paolino did for Fastpotify [2] - granted there are some rough edges for sure, but the slim diet trimmed down and performance gains were wrothy.
First Claude installed 10GB VM [0] without asking, but OpenAI ships LibreOffice.
What's next? Somebody ship their monorepo verbatim?
Honestly, not sure it's worth having those app on your localhost at all.
I ended up uninstalling all frontier labs bloated apps and start using Google AI Mode + Antigravity CLI / Claude Code sometimes.
Someone may need to explain to me what is wrong with this sorry. Is it because it bloats the app with functionality that some users will never use? I feel like that is fairly usual for productivity/business apps generally.
Oh right, yeah I agree. It's the kind of thing I can imagine the harness downloading in the background anyway (or instructing the user to do) at some point so I can see the sense in just skipping that bit. Kind of comforting they just do it the same way the rest of us do - if it ain't broke and so on.
It does, however, introduce a potentially enormous attack surface into ChatGPT, along with creative opportunities for less security conscious individuals and LLMs.
I'd like to know OpenAI's approach to updating these things - their auto-updated is pretty aggressive already, but does that cover their vendored cached apps too?
Yes, that's what I mean - maybe that didn't come across cos I said "bloats". I work for a business that builds web apps for corporates - LibreOffice is bundled in most of the repos of ours that I've seen, a bit like Imagick is in the broader sector.
Imagine the enormous complexity of office file formats if your business is literally building coding models/agents and still you choose to bundle LibreOffice.
I wonder if this says anything about the capabilities of AI. If it's better to bundle an entire headless office suite than ask your AI to build support for relatively well documented formats (or even to extract the file support parts it needs from Libra Office), that seems to suggest AI isn't as good as human devs just yet.
I've noticed that when I have codex read/modify word files the live reasoning snippets often allude to LibreOffice, so that makes sense. I think it was a quick and dirty way for them to interface with docx and xlsx files?
Last time I used the Windows version it pegged all my cores at 100% usage for some reason. The machine became unusable. Instead I used Codex with JetBrains Rider (doing a C# project) and it worked flawlessly.
Also in the newest app I think the transcription feature is unusable. Ok, I can have a shortcut to start and stop recording. Wow, cool! Ok, but where did the transcription go? In my clipboard? To my cursor? Hey? :(
Ok, it's probably not a security decision. It's a common pattern with both storage and memory management to push most reservations to initialization, in order to cluster resource insufficiency errors to a specific install-time when the user or admin can do something about it. An excessive just-in-time approach in both storage and memory would cause OOM and Disk exhaustion to occur at many different times.
spinning up an entire copy of libreoffice sounds super heavy?, if someone here is actually using chatgpt to edit docx documents then they can feel free to use us.
vespper.com
Indeed, but that likely wouldn't have stopped someone from submitting it with a misleading title. HN is known to get a lot of misleading titles submitted and to have to change them. The <title> tag is better, it doesn't say "a full copy". In the screenshot it shows "headless" in the filename. I would simply add the tiny detail of headless to the <title> and use this title for HN: Codex Bundles Headless LibreOffice
(I made a similar comment in a different post by Simon Willison yesterday about GPT Work)
I am unsure the direction that AI assisted document creation work will go in. I am opinionated and building something in the space. In this reply I discuss my view + what I have been building.
My opinion is: We now have AI, this new amazing flexible tool. We can throw it at any problem. But in terms of document creation we have a choice between old fashioned siloed document formats (.pptx, .pdf, .xlsx, .docx, etc.) and a freshly rendered - slightly randomly styled - html site with some basic javascript within it. I think these combinations are odd and do not maximise the powers of AI.
I've been building something called SmallDocs [0][1] which is a new take on work documents. It's all Markdown, but it always renders (100% privately) on the SmallDocs site. This means the SmallDocs renderer can convert recognised Markdown combinations into powerful traditional document formats [2]. For example, we convert a ```cells block into an in-line spreadsheet you can export to Excel.
This gives an agent the ability to express itself with a great deal of depth and flexibility. For example, your agent can produce a single data analysis "SmallDoc" with text, charts, spreadsheets, etc. [3] I find that combining formats quickens the speed I can understand a topic.
SmallDocs also have standardised and pretty boring styling. This means you spend less time understanding the layout of a flashy HTML page and more time on the content.
I also believe a pre-determined rendering engine has a lot of advantages over a freslhy built HTML artifact. It allows you to build in lot's of useful defaults that the agent doesn't have to code from scratch. These can be small things, for example, every time your agent renders a Markdown table in SmallDocs you can instantly copy it as a CSV or a PNG. And these can be bigger things, such as a rich slides DSL with solid styling defaults, which saves your agents a lot of tokens and results in consistently attractive HTML slides [4]. (Slides can also be automatically exported to .pdf and .pptx.)
I've been at it for a few months, and am still working on the project. I am looking for feedback and open source collaborators. Thanks for reading!
Walnut is the .NET and OpenXML backend. I think the point parent was trying to make it that it shouldn't be surprising Codex bundles runtimes for damn near everything.
I still don’t understand why with all their cash these companies dont redo their apps in Rust or native. They are all so heavy and dog slow. There are already some very fast cross platform (wasm too!) libraries that can do what poppler does as well as parse and produce various office file formats. Because 2gb is crazy town, these things could be around 100mb, just throw some tokens at the problem.
Just throw some tokens at the problem. I’ve vibed up a Rust Crux hybrid app that runs well on macOS, iPad and wasm and does some pretty complex xml manipulation and other document work. Absolutely smokes electron and you get native UI.
"ports like this" skips the part about Microsoft/enterprise software having a known and well tested surface area, the few examples we've seen are exceptional cases I suspect
Especially when there are three different versions, and each has a different team, and they all can work together at the same time. Crazy amount of tech supporting it that breaks a humans context let alone a models context.
Ever letter is it's own object and they stitch it into the visual view. When you type one letter is turns a single word into multiple objects all versioned objects.
Can't imagine all the crazy race condition protections baked into that.
A full implementation/rewrite of something like word, which is pretty complex and the quantity of edge cases is insane, in a relatively short amount of time, months, is very hard.
If they succeed with AI it will be huge: it's basically not possible to do it today with humans, no matter how many people you put on the job.
Me neither, but this is exactly my point: nowadays, no one will trust an "overnight word written in rust", unless someone prove that an "overnight word written in rust" is good enough.
And big AI LABs, with basically infinite tokens, are the only one in the position to do it.
Even then, I would not trust an AI lab as Microsoft does have a long history of support for word whereas I’m not sure the level of continued support from AI labs.
*support including bug fixes, vulnerabilities, continued user testing, interop with other services, standards, etc
Right now even OpenAI has its own copy of Overleaf (for latex). I’m not in the same circles as it’s intended users, though I haven’t heard any major use of it since the splash.
I mean, aside from all the NP Hard sub problems (I might not be reading your satire though), the real hard problem is that a "product" is not just software, but an ecosystem and a promise of maintenance of the abstract user experience & quality of it.
On top of everyone else’s great points, if you make your own “fork” of something, then you have to consistently maintain it. Which can be done with tokens, but an extra cost with something that’s not as user tested.
Ah good point, I thought this was coming across from the "recreate" your own approach. I would fully agree with you on using native frameworks, though the eletron desktop is a great "entry" onto desktops ensuring companies only have to update 1 source, as opposed to natives everywhere.
You should go actually try to make any basic automation work around these systems.
They purposely obscured, google doc is another example they completly hide the dom!
I spent months fighting word processing systems and ended up shipping libre. There's almost zero alternatives without that becoming your entire company.
Would be nice if they donate to LibreOffice then, to improve the support of various MS Office features in files, as well as comparison/diffing features. Win-win to everyone.
It's like that scene in the Simpsons when Bill Gates comes to buy out Homer:
"You don't think I got rich writing a bunch of checks, do you?!"
As much as I would hope they would... I don't think that's in character for sam altman.
Sam "Its only Open until it does not benefit me anymore" Altman
They will never do this
[flagged]
Good thing that "would be nice" doesn't entail that they have to.
Sorry, I can't understand what you mean by that.
Do you mean that it's good that companies can profit over people's mostly voluntary efforts for free, or Free Software is meant to be used for free and never supported in any way, or what?
I'm at a loss here.
They just imply them not having to doesn't dismiss the original comment, thread being more about morals than laws.
That being said, hoping for any financial support from AI companies would be really naive. Using others work without retribution is at the core of their model.
> That being said, hoping for any financial support from AI companies would be really naive. Using others work without retribution is at the core of their model.
I have no such expectations. They believe that they own the world and owe nothing, as you said.
They have correctly identified that they own the world and owe nothing. If you don't like that, should've used a different license.
I don't use Expat, BSD, CC licenses which allows unattributed free contributions. Nothing I use is permissive.
OTOH, do you think they care about source available restrictive licenses or Copyright laws, or laws in general?
If you believe so, I have a bridge which you can customize with a text prompt for sale.
You are allowed (and encouraged) to do good things without being obligated to.
I think it would be immensely cool if OpenAI donated some of that crapload of AI money to the people behind LibreOffice to help with development - and then having like a blog post about it or something would already improve the project's visibility a bit more (hey, every bit helps). What's peanuts to them could help with the sustainability of the project a whole bunch!
> You are allowed (and encouraged) to do good things without being obligated to.
We're absolutely on the same page with you, and I try to do my best with what I can in that regard.
On the other hand, I see a perspective which thinks that companies are entitled to use everything for free and don't need to support the Free Software ecosystem because it's an externality that they don't have to care for, which bothers me a lot.
What I was trying to understand that whether this comment was supporting that perspective, or is there something I'm missing entirely.
You misread that comment so much that I'm not sure going too deep here matters much.
I might have. I'm a human with a different native language. Sorry if that offended you. Was just trying my best.
Nobody is offended. I'm also not a native speaker.
You are not allowed to do good things. The penalty is more subtle: instead of cops showing up to arrest you, you will be outcompeted in the market. It's really hard to see when this is happening and course-correct, so all rational actors are doing their utmost to prevent it at all times.
[dead]
What does donation does for open source? Surely it wont come close to pay talented developers who create it. For cloud cost, there are few companies already giving generous free tier for open source.
The only thing that donation could pay for is marketing e.g. events and meetups.
That's not true at all. Donations are the biggest source of income for The Document Foundation, the non-profit behind LibreOffice, and have been used to pay developers who've joined the team in recent years:
* Michael Weghorn (accessibility)
* Jonathan Clark (language and scripting support)
* Neil Roberts (scripting improvements)
* Dan Williams (macOS support and general UI improvements)
How much do they pay them?
They don't disclose individual salaries but you can check their annual reports [1]. About 1M € among all the developers.
[1] https://www.documentfoundation.org/financials-and-reports/
It obviously depends on the project and the scale and duration of a donation, but plenty of open source projects have benefited from donations. Donations can and do pay for developers, as well, part time or full time. With LibreOffice, you can answer your questions directly by browsing https://www.libreoffice.org/donate/ and as a non-profit you can easily find more detailed reports: https://www.documentfoundation.org/financials-and-reports/
> The only thing that donation could pay for is marketing e.g. events and meetups.
You do realise there's an insanely large gap in-between "everyone is a volunteer" and "everyone is full-time staff", right?
you people are always mixing up the legal thing to do with the right thing to do
I agree that it would be the right thing to do. Which is why you have to make the best attempt to make it the legal thing, because people looking to make money will not care about what's right. So, it makes sense to point out the disconnect when people use and promote pro-corporate licenses and then get upset when corporates follow them to the letter and provide them nothing but demands in return.
If you want a mutually beneficial community, you should contribute and distribute using a license that requires it.
> because people looking to make money will not care about what's right
This is two-sided: making a kind of license mandatory also shrinks adoption if it is more restrictive. So, even if I acknowledge there is truth in your side of the story, there is also another at the other side, as usual.
How many people use GPL-licensed software as opposed to MIT licensed?
That is not the problem of GPL. I'd rather have high quality software with patches shared back and always being able to see the code than some popular software that eventually is used in some corporate environment without the ability see what they changed.
Regardless, who cares about "adoption?" That's not the original point of open source which was that if you're working on something and you wanted to share it, you could, without any expectation of usage, merely that it might help just one extra person out there. It's simply human ego to care about adoption and GitHub usage and stars especially have accelerated this.
> and you wanted to share it, you could, without any expectation of usage, merely that it might help just one extra person out there
Related: how do you think you can attract more people, by setting a restrictive copyleft that some people will use in their spare time or by attracting even corporations with money that will end up committing to a repo that is used in half of the world?
Note that I am talking about adoption bc thanks to adoption things just do not get rotten. If you make a piece of software and set a license that noone wants to touch, you will see it stall and die in front of your face.
Do not take me wrong, I mean, I think it is fair to contribute back, collaborating, sponsoring and so on. But it is a fact of life that if you make certain choices you make adoption more difficult with all the consequences it entails.
I do know what the original spirit of such licenses is. I was talking about real side-effects these choices have.
Why would I care about attracting more people? Not every piece of software needs a hundred contributors. As long as it works for me and maybe someone else gets use out of it, that's all that's needed in the eyes of the original spirit of the licenses. Stallman just wanted to fix his printer, not continuously work on that code for ten years.
> I agree that it would be the right thing to do. Which is why you have to make the best attempt to make it the legal thing
Do you believe that in an ideal world, any instance of not "doing the right thing" should be illegal?
But laws are just encodes morality.
Absolutely not.
It was illegal to harbour escaped slaves. Or hide Jews from the Gestapo.
Laws have nothing to do with morality. Or justice.
Well this goes into the debate of "is morality absolute or relative" which gets religious fast and there's more books on the subject than we have time to read.
I actually think that's a separate debate.
The question of "are laws there to enforce morality, or enforce public order?" is the key one. And, I think, very easily settled by looking at the laws we choose to implement. Almost none of them enforce moral behaviour (e.g. you must give 10% of your income to charity), they're all about enforcing how we interact and how we're ruled.
It's not really that "absolute". Laws are not all made the same. Some start as a reflection of what society considers "right" at the time. Then the laws fall behind as society's morality reaches a tipping point. So the society pulls that part of the legal system behind it. Other laws are progressive, and they pull society's morality behind them. Some are driven by/for the majority, and some by/for the elites.
But they all reflect the morality of society to a degree, whether the democratic majority, or the powerful minority.
That was the morality at the time.
Yes they do, but not with a philosophical concept of morality, but merely those of the ruling class/majority.
>It was illegal to harbour escaped slaves. Or hide Jews from the Gestapo.
Yes, of course. Morality is relative. In a slave-owning society, harbouring escaped slaves is immoral.
It is somewhat interesting that the version of morality an individual possesses always feels to that individual as an absolute.
"Of course it's wrong to beat your wife!" says the person who beats their children in a society that has only recently ceased infantilizing their women (USA circa 1900 +/- 30 years).
"Of course it's wrong to own slaves!" says the person whose society only recently began protesting against and/or illegalizing slavery (USA circa 1866 +/- 10 years)
They say this not knowing that had the event of their births been moved a few decades in the wrong direction their morality would have shifted with it.
Those same people might have said "Of course its wrong to beat your wife with a rod thicker than your thumb!" or "Of course its ok to own slaves as long as you treat them well!" at the same point in their lives had they been born maybe 30-50 years earlier.
The one I find fascinating is eating animals.
We currently eat animals as a normal part of our diet (for most of us, including me, anyway). To do this we treat the animals horribly. Incredibly badly. And we know it.
It's very easy to see how society's morals will probably change on this, in fact are changing on this, and how in 50 years' time our current stance on eating animals could be seen as monstrously immoral and indefensible.
Animals eat each other. Often in ways more "horrible" than what we do to them (in quotes because nothing in nature is horrible. Horror is a human notion).
Animals are not moral agents, and eating them is not different from eating plants. Both are part of the biosphere that we manage to our benefit.
Animals don't have a choice about eating each other. We do.
And there are plenty of people who would vehemently argue that eating their pet puppy is very, very, very, different from eating a plant.
And to complete a particularly cultural PoV, there are many people eating "pet" chickens, "pet" guinea pigs, goats, et al about the world.
Good arguments, particularly in Australia, for eating wild pigs, clean skin bulls, camels, donkeys (mainly for pet meat IMHO), etc. Kangaroos, unculled, explode in number past the sustainability of their landscape and litter the ground with bones - humans estimate a cull target and shoot to reduce populations, only eating a few themselves (leaving many on the ground for "nature").
I'm native, and my ancestors were called "dog soldiers" because we would bring dogs with us to war, and when rations got a little tight we would throw fido into the pot. Eating dog is generally considered abominable when you love them as pets but it's a common thing in many societies and not wrong.
I will say though, I would only ever consider eating a dog in a life or death situation.
If there was no absolute need for me to eat a dog then I would not do it, and even if there were it would be a difficult moral dilemma for me that should I survive could possibly haunt me for life, but for my ancestors it was a common occurrence.
[dead]
Funny how morality so often benefits incumbents and the powerful.
Many of them are, but they're focused on big picture issues and preventing harm. Most of morality has no legal force.
That's genuinely hilarious.
Who decides what the right thing to do is? Everyone has different opinions.
Mostly individuals decide what they will do, and then communities decide if they respect that or not. Doesn't exactly apply to companies tho, since they're functionally sociopaths.
Yes, each individual has individual notions on what the right thing to do is, is my point. There is no objective reality to it.
"you people" means people that always mix up the legal thing with the right thing? It's tautological to say they're always doing that because that's how you defined them! Are you trying to say that you've encountered other people doing that before too and you've built up an annoyance with them?
Surely "the right thing to do" includes some element of the authors' explicitly stated preferences about how they wish to be treated.
In this case, they chose -- explicitly -- to NOT require any payment or contribution from anyone.
Your feelings about what constitutes "the right thing to do" are apparently different from those of the authors. You believe you know better than they themselves do how they should be treated.
They clearly would like donations, but choose not to require any payments.
Your line of reasoning seems to be along the lines of "anything not forbidden is compulsory" which is not a good place. Having the choice to donate but not being required to is good.
And yes, I think that if OpenAI is choosing to include an entire copy of LibreOffice in their product, it is definitely the right thing to do to sling them a donation. Note that the moral thing to do is not always the required thing to do, or even the legal thing to do.
More like, don't expect anything if not forced. Most people only generally pay for things if there is no other option. It's about what's moral (even then debatable as everyone has different morals) versus what's realistic to expect.
The Guardian's funding model [0] proves this wrong.
People will absolutely pay for things voluntarily if you ask them, without forcing them to.
[0] https://www.theguardian.com/membership/2018/nov/12/katharine...
In a nutshell - voluntary funding by readership. No paywall. You can read as many stories as you like for free, and donate if you want. It works.
I've always wondered how they are actually making ends meet, if at all, that is, what their budget looks like.-
That article has no detail. How much did they make? They said they hope to break even in 2019 so they weren't profitable, what are the latest stats? Compare this to NYTimes which has been crushing it after implementing their paywalled subscription.
https://news.ycombinator.com/newsguidelines.html
> Please respond to the strongest plausible interpretation of what someone says, not a weaker one that's easier to criticize. Assume good faith.
> Surely "the right thing to do" includes some element of the authors' explicitly stated preferences about how they wish to be treated.
It does! And they wish to get donations. There's a button right at the top on the site making that clear.
> In this case, they chose -- explicitly -- to NOT require any payment or contribution from anyone.
Yes, so what? It is true that they wished to not require payment. That is one of their wishes, but they have more than one wish. And if they required payment, that wouldn't be a donation anyway.
I actually bundle LibreOffice with my app too and the reason is reading files, especially old xls files. Since I'm bundling it I'm now using it for everything docs related but the specific reason is those old files. I couldn't find anything else that I could just drop it and feel confident it'll just read anything I give it.
[flagged]
>How much money have you contributed back to this seemingly indispensable project?
Perhaps it's time for you to become familiar with the terms of the Mozilla Public License, under which Libre Office is released. There is no requirement for monetary compensation.
No requirement doesn't mean "don't be a mensch"
Yeah but like, we don't know if OP is making any money off this, let alone significant money. Let's not instantly hold them to the same "please contribute or you're dragging things down" standard as a zillion dollar corporation.
> we don't know if OP is making any money off this
I'm not, and don't have any intentions to monetize it.
You believe you know better than the authors themselves about how they ought to be treated?
They chose -- explicitly, voluntarily, knowingly -- to give the thing away for free. That's their right for their own creation. Your preferences don't supersede theirs.
You've emphasized this point more than once, but I don't think it's a good counterargument to the GP. It is equally valid to say that they have explicitly (voluntarily, knowlingly) chosen to accept donations for their work.
By profiting off their work and not supporting them you are making your own choice. It says nothing about the authors' preference.
There is also no expectation to bash people who do not want to donate anything.
I don't know what a mensch is but if they wanted to be compensated for their software they should not have released it as Free Software.
Mensch is German for Human.
[flagged]
Does that really mean that it's bundling those apps from the start or did it just download and install them at some point to do some local work on some prompt or job you ask it to?
I don't see it making much sense to bundle it. I'm sure a LOT of LLM prompts are related with docs, excels, powerpoints etc, etc but don't really see it worth it for it to be bundled on the codex app from the get go, because otherwise, why not also install dozens of other apps?
I'm not sure. Someone who hasn't installed the ChatGPT (or Codex) apps yet could confirm this by installing the apps, seeing if that ~/.cache directory exists, then try running a prompt that needs Python or Node.js or LibreOffice and see if it downloads them when needed.
I've never installed the ChatGPT app on my Mac until today. I ran the app, signed in, and I see the same.
% ls ~/.cache/codex-runtimes/codex-primary-runtime/dependencies/native/libreoffice-headless
libreoffice manifest.json
On a Windows installation I see this:
So doesn't seem bundled with all installs at least.Is this perhaps because the aim is to read Office documents and there are (maybe, I don't know for sure) default components within Windows that can do that?
I don't think there are.
Even when you have the MS Office suite installed, it doesn't really provide a good interface for LLMs or automation, so AI tools don't really use it.
And libreoffice has some really useful and easy to use tools for document manipulation and creation hiding in the background.
Codex always try Libreoffice first on my computer.
Notably: this did not exist after I installed the app, it existed after I ran the app and there was the long startup screen. Presumably, and I'm not sure I'm interested enough to redo it all and find out, that long startup screen involves the default skills plugins setting up their environment and one of those pulls it as a general app requirement.
I also saw this present after first run on macOS but not Windows.
[flagged]
I have had the Codex/ChatGPT app installed for a few months, and can confirm that there's a 422.9 MB file named LibreOfficeDev.app in the above path.
More notably, I don't use Computer Use or any of the fancy features, just Codex for agentic coding.
> why not also install dozens of other apps?
because other apps are less likely to be useful, and there's diminishing returns
The new app is an unbelievable mess. Settings are senselessly organized, too. The whole thing has this aesthetic slickness and then underneath it's like the people who make it have never even used it.
It's not surprising that it's pulled in absolutely massive dependencies, although I'm not sure it's the wrong call on some operating systems. LibreOffice is pretty tried and true.
Personally, I like the 3-pane organization (sidebar, chat, browser). I turned ChatGPT into my bookkeeper and social post writing/kanban space, and it works well for these script+browser workflows on desktop.
However, all of this is confusing:
- the ChatGPT/Codex split on desktop
- Chat/Work split on mobile
- how you remotely access each chat from your phone (some of my most valuable chats are buried in Remote)
- which chats propagate from device to device, and which remain on that device
> - the ChatGPT/Codex split on desktop
Do tell, cause I run the "ChatGPT" program on Windows to use both the normal Chat and Codex (side menu items). I think its a more recent change.
This is from a recent update, and I'm on macOS. I had to re-download it, not just update from within the app.
This new version has tabs for ChatGPT and Codex. The ChatGPT tab seems way less powerful; Codex is basically a coding agent with a UI and browser built in.
Pretty sure this is the old Codex app with the ChatGPT tab bolted on. It's great in some ways, but needs work in others.
[dead]
The thing that blows my mind about it is that they straight up copied Claude Code and tried to frame it as some sort of incredible accomplishment. There are no new ideas, no insightful UI/UX paradigms, no killer features. They say money can't buy taste. The ChatGPT/Codex app is proof that it cannot buy creativity either.
which is really funny/sad when you see openai staff doing victory laps whenever claude code copies one or two small codex features like /goal.
Codex, clone Claude Code, make no mistakes they also didn't make.
They removed the global shortcut to show a portable chat overlay. That one entrypoint must've been the source of at least 80% of my chats, yet apparently it was considered too vestigial to keep.
Can it be reassigned under Settings / Keyboard shortcuts?
Yes, although it's buried among a huge number of other shortcuts now, and not particularly easy to search for.
Did they restore the functionality itself? Last time I checked the overlay was just straight up not a feature anymore.
Where are the AI-will-render-software-engineers-obsolete and/or vibe-coding apologists? They can make all kinds of nice-sounding arguments, but if AI is contributing to a degradation in product quality, their arguments cannot stand up to the reality we see with our own eyes. The proof of the pudding is in the eating, and all that.
It is the same with Claude Code. Pretty much each change Anthropic makes to it now lowers its quality. Just yesterday they auto-updated it, and now backspace in the CLI does not work reliably. It also insert the enter key command when there is a line break in text that you are pasting, causing fragments of the prompt to be sent prematurely. What the heck! And pretty much all the regressions I have experienced this year have also not been fixed.
HOW DOES IT WORK FOR YOU PEOPLE?!
Istg on windows, I can't get codex app, new chatgpt or chatgpt classic to work without hanging on even a moderately sized chat. I tried all of the different tricks people recommended but that shit just crawls. It was stable at some point, classic that is, but then it started being a laggy mess.
I've uninstalled new chatgpt/codex app. I can't access phone chats on it, I can't use the desktop allocated chat messages on it. I have to use up codex limits. I am so surprised that OpenAI ships that hot garbage on windows.
Windows has never felt more archaic than now. I can't imagine trying to do work on a Windows machine in the age of LLMs.
If there is anything that LLMs are rock solid at these days, it's unix terminal usage.
They're also great at powershell, you just need to tell it to do so. sh is neat but it's 55 years old, there are newer and better shell environment concepts out there and the robots can handle them well too, try it some time!
PowerShell unfortunately just isn't that first-class, even on Windows. You'll inevitably discover, if you do this, that certain things simply can't be automated via PowerShell, that some PowerShell modules wrap or lag behind older Windows CLI tools, that various things you want to do still require manual registry hacks, etc.
Try starting from a blank slate Windows machine and making a commitment to only changing settings via PowerShell, and ideally only declaring them using DSC. You'll soon discover settings where the best you can do is snapshot the registry, change a setting in the GUI, snapshot the registry again, then take a diff so you can write the registry change into your PowerShell automation. If you're on a corporate machine, you'll also likely find many corners of PowerShell that you need closed off to you, anyway.
At the end of the day, Windows is not friendly to automation because it's not CLI-first (not culturally and not technically).
Your argument is directed at Windows, not PowerShell. The shell is just a shell, if a certain thing you're looking to configure doesn't have an easy cmdlet, that doesn't mean powershell is bad, just that MS didn't give you the easy button. Similar to many unix tools, some of what you need to interact with has a dedicated CLI, other things have you poking at the configuration database directly (ini or yaml or whatever for unix, registry for windows).
If you don't like the Windows style of configuration, run powershell on linux - it's awesome there too!
I'm not sure why reading and writing the registry is considered a bad interface for programmatic system administration.
I realize text files can be processed by utilities for working with text files. And text files can be read by humans without any tools, and in that sense are rather universal.
I wonder what I'm missing.
I'd go so far as to think an OS that had a database at its core, or perhaps a persistent lisp would be even more programmable and legible.
Maybe better tools for dealing with structured data would help this?
How do you work on Windows in the age of LLMs?
That’s easy: you activate WSL and then ask the LLM how to get networking and stuff working since they changed it with WSL2. You need a config file flag to setup network mirroring now.
Mac Neo can be had for $600 now, and it runs Codex incredibly well!
But even on the Windows machine, if you Tailscale into a free tier VM for the workloads, you'd probably have a much better time.
Just leave Codex itself on your machine, if you set up computer use it will happily set up all of this for you while you have lunch.
> Mac Neo can be had for $600 now
Maybe a used one?
https://www.apple.com/macbook-neo/ has it for ~$700
Kind of, Swappa has new sealed units with the original warranty (and the warranty timer only starts when you set up the device), but indeed these are resale and not directly from Apple.
Do you have any tips for running Codex on the Macbook Neo? Have you changed any setting? On mine, it stutters on every single chat, and I don't even have any plugins installed.
Are you on the recent update that handles long chat sessions much better? That made a big difference. Biasing towards lightweight and fast tool alternatives (uv over pip, bun over npm, ripgrep over grep, etc).
If that still doesn't resolve it, a free tier VM might be the move. I suspect OpenAI will be bundling some kind of VM with their new Astra release, which Sama said yesterday will be released soon (this week maybe?). If this new model supports much longer running tasks, you'll want a dedicated box that can run 24/7 even when your Neo is closed and asleep anyway.
One thing I've found - these things are pretty good at troubleshooting desktop problems. If the codex app is running slow, I'll note that it shouldn't be, and also you might get more traction than you'd expect asking the codex app why it's slow.
Almost like it's... vibe coded.
yeah, that seems obvious by now.
> The new app is an unbelievable mess.
How so? On Windows, I like it (version 26.825.51511).
Works fast (like modern Claude Code desktop, their old versions were bad), has pretty okay UI (could have an option for wider main text display, like ZCode added), allows you to change the fonts and shells and some of the layout stuff.
I mean currently I have Paseo hooked up to OpenCode that runs the actual models and often that works a bit better for me, but as a standalone desktop offering, the ChatGPT app has been okay in my experience. I can kinda see why ZCode copied them a bunch (though ZCode also lets you run 3rd party models, which is actually preferable to me).
I do like the idea that Claude Code desktop had in the earlier versions, 3 tabs - chat, work, code, except they kinda went in the direction of merging chat and work which was very ehhhh. The ChatGPT app doesn't even have a proper split between chat and work/code.
Probably vibe coded right?
And when you go to their forums it says "This forum is not for discussing the ChatGPT App..."
..like excuse me? Where the fuck else would we post feedback about it?
Just tell ChatGPT what changes you want in the next version.
Is that what it is using to render and manipulate MS Office documents? That'd explain the poor rendering of some of my files. Bundling all of LibreOffice seems like a pretty huge dependency.
What's ironic about this is, afaik there's no programmatic way to get a screenshot of a PowerPoint on windows other than opening up PowerPoint and screenshotting it. I only discovered this when I first tried out Anthropics official PowerPoint skill when it came out this winter.
If anything happens from this, I hope it forces Microsoft to address some of its long standing hostile to power users issues so they can stay relevant in the world of AI tooling.
This can absolutely be done programmatically. I just added the ability to do that using PowerPoint for Windows yesterday in my uv/python tool `markdown-pptx`. Codex added the functionality in less than 5 minutes.
https://github.com/pseudosavant/markdown-pptx/
For those that are interested, this inspired me to create a tool just for exporting images and PDFs of Word, Excel, and PowerPoint files. Check out the repo below, or if you have uv installed just run `uvx office-export skill install` or `uvx office-export --help` to check it out.
It uses Office for Windows, so it is Windows only. I don't currently have access to a Mac machine, so I can't build in Mac support yet.
https://github.com/pseudosavant/office-export
Thanks for sharing, now im wondering if they did in fact grant my wish since I messed with this in January. Im lucky my job does not require me to make any pptx presentations.
I have made puppt cli for this, it includes high dpi rendering per-slide/all-slides and in place editing
https://github.com/artpar/puppt
it allows your llms to see the ppt files structurally apart from just rendering it
Cool project! I'm playing around with some similar stuff, but via uv/Python. Impressive you aren't leveraging any other existing libraries for OpenXML parsing, editing, or rendering. Any especially tricky gotchas you've run into for this tool?
Yeah thanks to LLM hill climbing and PPTs being easily available and they being nothing more than just xmls this did not involve any gotchas, just a about a weeks worth of goal chasing with manual verification. I did have to stop LLM into hardcoding a lot of times trying to escape the actual goal.
But based on this I thought I could make something similar for cad files, and they turned out to be an entirely different monster. the cad spec is like 1000x bigger than ppts, cad files themselves were hard to gather for test targets. 70-80% of their spec is public and remaining is driven by private vendors. the format itself is in binary. The LLM has been chasing that goal since about 2 months now and its nowhere close.
I have a skill that instructs ChatGPT/Codex to verify the rendering using the Mac versions of Microsoft Office. Even without registering, you still can open files read-only, which is enough. Apparently Office refuses to open some Open Office XML documents that LibreOffice is fine with, so that's another reason to use this. After a few times, Codex ended up storing some memories to stop producing broken files in the first place.
I generated the skill originally for ChatGPT 5.5, so some of these may not strictly be necessary anymore with later models. But posting here in case others find it useful: https://gist.github.com/telotortium/844386f762c4b3bab49999ba...
For a docker image of mine I was bundling the full version of LibreOffice as well but I managed to get some space savings by bundling just the no-gui version.
Seems to match the screenshot in the blogpost but libreoffice-headless still shows as 429.7 MB.
> Bundling all of LibreOffice seems like a pretty huge dependency
What's the alternative library you see?
pandoc
Why not computer use or using the tools the user prefers instead? The primary office suites have APIs/CLIs now
If you've ever actually gone down this route you will try exactly this realize how much of a cluster f these products are and just use libre.
I did the exact same thing in my AI system. Spent an ENOURMOUS amount of time trying everything I could and in the end libre was the only thing even somewhat functional.
Easily 2 months of my life lost to these god forsaken systems. APIs and CLIs sound reasonable until you actually attempt anything in this space.
Computer use is exactly the same thing. Go try this: go to a google doc and dev tools check out the dom and now do the same for a word doc. Eye gouging pain of trying to get anything to work.
Computer use is slow and can take control of the application focus. I’ll be doing things while Claude runs in the background. Suddenly it decides to open the app and try to do something + screenshot it.
That's where the CLIs come in for me, I'm not going to waste tokens on screenshots and input device manipulation
https://devblogs.microsoft.com/microsoft365dev/getting-start...
https://github.com/googleworkspace/cli
Runs in the background now
https://x.com/ClaudeDevs/status/2095226982644830648
I don't know how many times I've had to yell at codex or claude to use/implement headless versions of whatever it's doing at the time, interrupts me trying to multitask and play Battlefield or Factorio while they work :P
don't try Dyson sphere project (/s, its acrually really great), but maybe try x4 foundations, I'm contemplating how I might have my agent help manage my empire
Can't you run this under a different user or in the same, but with another instance of the desktop server?
Another good reason to sandbox them into a VM :P
Apache POI
I don't think that's anywhere near equivalent. That's for reading and writing Microsoft Office docs. It has no office functionality. LibreOffice has a full API, for example to run calculations on spreadsheets [1].
The goal of bringing in dependencies is so you don't have to duplicate the functionality, in this case, crafted over decades of effort.
[1] https://wiki.documentfoundation.org/Documentation/SDKGuide/C...
POI can run calculations. [1] That doesn't make it a full office suite but it does a lot.
[1] https://poi.apache.org/components/spreadsheet/formula.html
[dead]
[flagged]
Just the headless version looks to be bundled. The title as posted might be incorrect.
Yes. If you have word you can instruct to use word via com or AppleScript.
There is a serious threat to Microsoft here, if everyone starts using AI for generating and updating Office docs. At some point Office will become just a viewer.
im stoked for that outcome, standard document tooling should not live behind subscription models anymore. i dont care that microsoft spent zillions bankrolling education systems and companies to fall into this cultural lock in over the decades
whether they like it or not spreadsheets word docs etc are just ubiquitous parts of existing in society at this point you're gonna need to reach for these tools eventually just to apply for jobs or do homework
You assume tokens will be free after these get their monopoly positions? Actual libre office is actual open source running on weak hardware. Truly free.
And I suspect we will look back at MS with nostalgia once Altman and Musk get their ai imperiums.
Don't worry, they are ahead of this.
Satya said some time ago that they expect soon to have more agents using Microsoft software than humans, and are working on transitioning their focus from serving humans to serving agents.
https://www.news18.com/business/satya-nadella-announces-micr...
So they will switch to per-agent pricing instead of per-user. Fine, but that doesn't change the fact that Microsoft Office will become a just bunch of viewers as far as human usage is concerned. As far as generating Office documents, you can do that without using any Microsoft code.
This is one that's already true and "everyone" hasn't figured it out yet. But you don't really even need Office as a viewer, PDF is fine (for printable/portable fixed-layout) or just HTML. "Office" is a product that doesn't need to exist anymore, at least for the core apps. For day-to-day office work, you probably shouldn't be using those legacy apps, you should be reviewing portable document formats and asking an agent to make the revisions that you want.
> For Microsoft, this shift means products like M365 will act as the foundational layer where AI agents operate. Users will still need places to store documents, manage projects, search files, and track workflows
They bet on the online office suite (M365).
... and without the license, crucially!
But why would openai and antrhopic pay them if they already libreoffice for free and why would users pay if they already have an Ai subscription
This sentiment is also why Microsoft crushed earnings this quarter. Their AI play is to create corpo-slop AI middleware, which sits between AI models and enterprise applications. Sure, others can go and build harnesses which can generate MS office documents, but MS is already doing it, and conveniently such harnesses will come with everyone's existing Microsoft 365 subscription.
The analogy is IBM. Just like IBM helped every old-money corporation on the planet figure out the whole "computers" thing 50 years ago, MS will help everyone solve the "AI" thing. The software will suck and will not really innovate, but it will make a ton of money
> The software will suck and will not really innovate, but it will make a ton of money
Microsoft’s goal isn’t to provide high quality software that outperforms other software, their goal is to provide an obvious and reasonably proximate answer to clueless execs trying to check things off of a procurement list so that existing contracts can snowball and competition is excluded.
We, collectively as a global species, really lost out when MS wasn’t divvied up in their anti-trust trial. Office as its own corporate entity would be in a radically different place right now, as would their enterprise customers.
I have not created or read any Word document for a very long time. I only create PowerPoint presentations a few times a year for work, which could be easily replaced with PowerPoint online or Google Slides or even just some markdown files.
But I have a license for the entire office 365 including Copilot premium.
Guess why?
For Excel?
I think they meant to view documents.
Likewise with PDF editing via AI. Way nicer than having to pay Adobe or some other shady software vendor for PDF editing ability.
If you don't have to edit files or you are not supposed to, they should send you a PDF, unless it's an Excel. Excel is a much better viewer for itself because of many reasons (explore the formula, sort, filter) including that usually its sheets are not built to fit a particular page format.
Haven't used MicrosoftOffice in the past 7 years.
Curiously, I didn't find any reference in the Open source licences section of the codex app.
Is this a MPL 2.0 violation?
Despite the title, I'm not sure it's actually bundled. Some of the skills plugins will download it on the first run. So it depends where they are grabbing it from rather than the presence of the binary on the system, but I haven't checked that deep into where they actually grab it.
The license itself may be present in the cache folder.
Alternatively, ChatGPT might happily disclose authorship and licensing if asked.
I'm not convinced of the argument that the fact that it is not bundled at download or even at install-time, would free them of the GPL responsibilities. And at this point.
I'm also not sure HOW the devs bundled libreoffice, whether they just mentioned in a prompt (use libreoffice), or whether they hardcoded a command (like apt install libreoffice), more likely the former, considering the recursive vibecoding nature of this software.
Whole lotta words to say that I don't know whether this is a GPL violation, but interested in the answer. If it is a violation, the likely fix will probably be yet another prompt that says something like "comply with licensing", which probably already exists, so a more specific "provide attribution (in a way that doesn't bother the user)"
> Whole lotta words to say that I don't know whether this is a GPL violation,
I don't need a lot of words to say it can't be a GPL violation since Libreoffice is distributed under the MPL v2.0 license.
https://www.libreoffice.org/licenses/
https://www.mozilla.org/en-US/MPL/license-policy/
I finally did find the license in
Copyright violation is the last thing one could accuse ChatGPT of.
Well, this one is particularly obvious, other one are more fuzzy.
[dead]
I think that depends on if they distribute it with the install package, or if they download it once installed.
Now someone please use ChatGPT/Codex or Claude Code to rewrite the entire LibreOffice source into a single Rust binary already! Just like Jarred Sumner did for Bun [1] or Carmine Paolino did for Fastpotify [2] - granted there are some rough edges for sure, but the slim diet trimmed down and performance gains were wrothy.
[1] https://bun.com/blog/bun-in-rust [2] https://fastpotify.rocks/
> rewrite the entire LibreOffice source into a single Rust binary already!
Why?
Java
First Claude installed 10GB VM [0] without asking, but OpenAI ships LibreOffice. What's next? Somebody ship their monorepo verbatim?
Honestly, not sure it's worth having those app on your localhost at all. I ended up uninstalling all frontier labs bloated apps and start using Google AI Mode + Antigravity CLI / Claude Code sometimes.
[0] https://github.com/anthropics/claude-code/issues/22543
I already have a copy of LibreOffice on my mac. It weights around 3GB. That extra copy is not appreciated
Someone may need to explain to me what is wrong with this sorry. Is it because it bloats the app with functionality that some users will never use? I feel like that is fairly usual for productivity/business apps generally.
I don't see anything wrong with it, I just think it's interesting.
Oh right, yeah I agree. It's the kind of thing I can imagine the harness downloading in the background anyway (or instructing the user to do) at some point so I can see the sense in just skipping that bit. Kind of comforting they just do it the same way the rest of us do - if it ain't broke and so on.
It does, however, introduce a potentially enormous attack surface into ChatGPT, along with creative opportunities for less security conscious individuals and LLMs.
You aren't worried about the provenance of the installed apps?
How do you mean?
I trust OpenAI to have installed apps that at least work well enough for their intended purposes.
You aren't worried that these binaries may have unfixed vulnerabilities?
That's the nature of installing software.
I'd like to know OpenAI's approach to updating these things - their auto-updated is pretty aggressive already, but does that cover their vendored cached apps too?
I think it's overbloating my computer
Actually, people do use and require the functionality, which is the point. The title as posted might be incorrect.
Yes, that's what I mean - maybe that didn't come across cos I said "bloats". I work for a business that builds web apps for corporates - LibreOffice is bundled in most of the repos of ours that I've seen, a bit like Imagick is in the broader sector.
Imagine the enormous complexity of office file formats if your business is literally building coding models/agents and still you choose to bundle LibreOffice.
I suspect that it’s used in headless clip mode to reliably convert file formats back and forth.
Reminds me of pulling in an entire JS framework just for a single button. The bundle size must be something else.
Reminds me of this joke https://medium.com/s/silicon-satire/i-peeked-into-my-node-mo...
I wonder if this says anything about the capabilities of AI. If it's better to bundle an entire headless office suite than ask your AI to build support for relatively well documented formats (or even to extract the file support parts it needs from Libra Office), that seems to suggest AI isn't as good as human devs just yet.
Or, it's dumb as hell to have an AI re-write Word every time it wants to output or present a document.
But let's focus on how this validates the belief that "AI bad."
perhaps onion2k meant that openAI could’ve reimplemented it once in-house on their side for the codex app?
[dead]
I wonder why they didn't try to discover if the user already has those binaries and use them before downloading.
Why would they? Storage [they don't have to pay for] is cheap! And just bundling it saves them time.
Preventing potential version/feature issues?
Because they vibe coded it.
Presumably this is for ChatGPT Work? https://simonwillison.net/2026/Aug/30/understanding-chatgpt-...
I've noticed that when I have codex read/modify word files the live reasoning snippets often allude to LibreOffice, so that makes sense. I think it was a quick and dirty way for them to interface with docx and xlsx files?
Last time I used the Windows version it pegged all my cores at 100% usage for some reason. The machine became unusable. Instead I used Codex with JetBrains Rider (doing a C# project) and it worked flawlessly.
Also in the newest app I think the transcription feature is unusable. Ok, I can have a shortcut to start and stop recording. Wow, cool! Ok, but where did the transcription go? In my clipboard? To my cursor? Hey? :(
There's no security benefit to doing this versus demand-downloading hashed-locked components on need.
Ok, it's probably not a security decision. It's a common pattern with both storage and memory management to push most reservations to initialization, in order to cluster resource insufficiency errors to a specific install-time when the user or admin can do something about it. An excessive just-in-time approach in both storage and memory would cause OOM and Disk exhaustion to occur at many different times.
Are they at least respecting the licenses (.i.e.: providing a verbatim copy of each license?)
It might be for their new Work product which can produce docx, pdf and pox files.
spinning up an entire copy of libreoffice sounds super heavy?, if someone here is actually using chatgpt to edit docx documents then they can feel free to use us. vespper.com
You want something heavier? They were trashing people's SSDs a few months ago. IDK if it's been resolved, yet.
https://x.com/bdsqlsz/status/2067964486615810369
DNS_PROBE_FINISHED_NXDOMAIN
probably uses it extensively to convert between LLM working on a doc and exporting it out to excel, word etc
having had to manually save some xls files by editing their xml, yeah it makes sense
My agent did it? I didn’t do it.
I don't see the problem?
Who said it was a problem? This looks like an observation to me, not an accusation.
Bundling LibreOffice with a chatbot app feels like peak software bloat. My hard drive just let out an audible sigh.
(This is more of a tweet than a blog post, it really wasn't written with Hacker News in mind.)
Indeed, but that likely wouldn't have stopped someone from submitting it with a misleading title. HN is known to get a lot of misleading titles submitted and to have to change them. The <title> tag is better, it doesn't say "a full copy". In the screenshot it shows "headless" in the filename. I would simply add the tiny detail of headless to the <title> and use this title for HN: Codex Bundles Headless LibreOffice
frankly how dare you
How is simonw to blame for somebody else submitting it to HN?
True, I feel like the entire HN community is to blame for this, particularly pg and dang.
Thanks Obama
I have a feeling you should learn about Poe's law: https://en.wikipedia.org/wiki/Poe's_law
Anyone quoting Poe's Law is clearly just a Nazi.
...
For those that can't see the sarcasm: https://en.wikipedia.org/wiki/Godwin%27s_law
I have a feeling you should learn about...
OH SHI~
(I made a similar comment in a different post by Simon Willison yesterday about GPT Work)
I am unsure the direction that AI assisted document creation work will go in. I am opinionated and building something in the space. In this reply I discuss my view + what I have been building.
My opinion is: We now have AI, this new amazing flexible tool. We can throw it at any problem. But in terms of document creation we have a choice between old fashioned siloed document formats (.pptx, .pdf, .xlsx, .docx, etc.) and a freshly rendered - slightly randomly styled - html site with some basic javascript within it. I think these combinations are odd and do not maximise the powers of AI.
I've been building something called SmallDocs [0][1] which is a new take on work documents. It's all Markdown, but it always renders (100% privately) on the SmallDocs site. This means the SmallDocs renderer can convert recognised Markdown combinations into powerful traditional document formats [2]. For example, we convert a ```cells block into an in-line spreadsheet you can export to Excel.
This gives an agent the ability to express itself with a great deal of depth and flexibility. For example, your agent can produce a single data analysis "SmallDoc" with text, charts, spreadsheets, etc. [3] I find that combining formats quickens the speed I can understand a topic.
SmallDocs also have standardised and pretty boring styling. This means you spend less time understanding the layout of a flashy HTML page and more time on the content.
I also believe a pre-determined rendering engine has a lot of advantages over a freslhy built HTML artifact. It allows you to build in lot's of useful defaults that the agent doesn't have to code from scratch. These can be small things, for example, every time your agent renders a Markdown table in SmallDocs you can instantly copy it as a CSV or a PNG. And these can be bigger things, such as a rich slides DSL with solid styling defaults, which saves your agents a lot of tokens and results in consistently attractive HTML slides [4]. (Slides can also be automatically exported to .pdf and .pptx.)
I've been at it for a few months, and am still working on the project. I am looking for feedback and open source collaborators. Thanks for reading!
[0] https://smalldocs.org
[1] https://github.com/espressoplease/smalldocs
[2] https://smalldocs.org/blogs/what-is-a-smalldoc
[3] https://smalldocs.org/s/46fWiAyF77T9c7tqYwAQqp#k=j78ZEOOrgo8...
[4] https://smalldocs.org/s/QrmeWMsULGS871nXQYOacB#k=ubOHH9QtTWp...
(And something totally different, your agent can also use SmallDocs to walk you through code files: https://smalldocs.org/s/JsI_-tWSH0UpSd_YXxVLPm#k=G5jLCYA4JUX...)
And wait till you find out about @oai/walnut
do tell!
Walnut is the .NET and OpenXML backend. I think the point parent was trying to make it that it shouldn't be surprising Codex bundles runtimes for damn near everything.
[flagged]
[dead]
[flagged]
[dead]
[dead]
[dead]
I still don’t understand why with all their cash these companies dont redo their apps in Rust or native. They are all so heavy and dog slow. There are already some very fast cross platform (wasm too!) libraries that can do what poppler does as well as parse and produce various office file formats. Because 2gb is crazy town, these things could be around 100mb, just throw some tokens at the problem.
Not that easy. Also, they have "priorities." Although their priorities are different than the users'.
Just throw some tokens at the problem. I’ve vibed up a Rust Crux hybrid app that runs well on macOS, iPad and wasm and does some pretty complex xml manipulation and other document work. Absolutely smokes electron and you get native UI.
Ref: https://redbadger.github.io/crux/
one does not just "throw tokens" at a problem, Ai is not that capable, and we are talking about MS Office file format, likely a NP hard problem
AI is especially good at ports like this where there’s a known and well tested surface area.
"ports like this" skips the part about Microsoft/enterprise software having a known and well tested surface area, the few examples we've seen are exceptional cases I suspect
*that only microsoft has access to.
These guys puposely obscure controls and understanding of these products 100% to prevent you doing a port.
Just go open a microsoft word doc in the browser and look at the dom.
Despair! Horror!
Especially when there are three different versions, and each has a different team, and they all can work together at the same time. Crazy amount of tech supporting it that breaks a humans context let alone a models context.
Yeah that's by far the most complex part.
Ever letter is it's own object and they stitch it into the visual view. When you type one letter is turns a single word into multiple objects all versioned objects.
Can't imagine all the crazy race condition protections baked into that.
But in case they succeed the return on image will be astonishing.
Can you expand upon this?
A full implementation/rewrite of something like word, which is pretty complex and the quantity of edge cases is insane, in a relatively short amount of time, months, is very hard.
If they succeed with AI it will be huge: it's basically not possible to do it today with humans, no matter how many people you put on the job.
I would agree a full rewrite of word which is very complex and take quite a bit of time.
It would be impressive of AI to make a 80% rewrite, though I fully doubt it would cover the 100% rewrite (disregarding long term support as well).
Why do you think it’s impossible for humans to rewrite word, especially even humans made it in the first place?
I think it's not possible with humans in a relatively SHORT amount of time (let's say 1 year).
I’m not sure about you but I would not want to adopt and ship an overnight “word” written in rust
Me neither, but this is exactly my point: nowadays, no one will trust an "overnight word written in rust", unless someone prove that an "overnight word written in rust" is good enough.
And big AI LABs, with basically infinite tokens, are the only one in the position to do it.
Even then, I would not trust an AI lab as Microsoft does have a long history of support for word whereas I’m not sure the level of continued support from AI labs. *support including bug fixes, vulnerabilities, continued user testing, interop with other services, standards, etc
Right now even OpenAI has its own copy of Overleaf (for latex). I’m not in the same circles as it’s intended users, though I haven’t heard any major use of it since the splash.
I'm not talking about that, but existing utility tools (in Rust) that can generate MS document format. Perhaps not perfect, but these work today.
I wouldn’t imagine recreating Apache poi would be a terrible reach for a human let alone a llm.
Anything beyond basic utilities though I have a slightly harder time seeing.
I mean, aside from all the NP Hard sub problems (I might not be reading your satire though), the real hard problem is that a "product" is not just software, but an ecosystem and a promise of maintenance of the abstract user experience & quality of it.
On top of everyone else’s great points, if you make your own “fork” of something, then you have to consistently maintain it. Which can be done with tokens, but an extra cost with something that’s not as user tested.
I’m not talking about forking, but using standard libraries and native frameworks instead pretending electron is a desktop app.
Ah good point, I thought this was coming across from the "recreate" your own approach. I would fully agree with you on using native frameworks, though the eletron desktop is a great "entry" onto desktops ensuring companies only have to update 1 source, as opposed to natives everywhere.
You should go actually try to make any basic automation work around these systems.
They purposely obscured, google doc is another example they completly hide the dom!
I spent months fighting word processing systems and ended up shipping libre. There's almost zero alternatives without that becoming your entire company.
What % of time, for a an average session, do you think is app overhead vs waiting for tokens? And there's your answer for why it's not a priority.
From OpenAIs perspective, resources on your computer are free and wasting them is inconsequential
Kind of. Eventually it gets too slow even for the OpenAI engineers using it, and then they need to fix it.
Jon Blow's response to this take was, "yes, which is why you have to work even harder to hide latency", instead of adding more on top.
[dead]
What makes you think Rust is automatically better?
(Also, "Rust or native" is a strange dichotomy. What's not native about Rust?)
Rust or native is objectively more performant and have smaller binaries than these web apps in Halloween costumes…
I think “or native” is a gesture at swift/objc for mac and C# or whatever people write windows apps in.