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.
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.
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.
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.
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.
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 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 type of file formats.
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.
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
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.
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?
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.
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?
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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).
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?
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!
Ironically, I feel like LLMs have really unlocked Windows work since they all know how to use Powershell and all the weird Windows commands/hacks that you otherwise either wouldn't even know about, or would have to Google every time.
I used to hate working in Windows, but now it feels roughly comparable to Mac (though at the risk of inciting an OS war, I do feel like Linux still beats both out...)
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.
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.
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.
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.
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. Each change they now lowers the harness' quality. Just yesterday they auto-updated it, and now backspace in the CLI does not work reliably. Pretty much all the regression I have experienced this year have also not been fixed.
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
Imagine the enormous complexity of office file formats if your business is literally building coding models/agents and still you choose to bundle LibreOffice.
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? :(
178 comments
[ 4.1 ms ] story [ 66.0 ms ] threadWhat's the alternative library you see?
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.
https://github.com/pseudosavant/markdown-pptx/
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
https://github.com/artpar/puppt
it allows your llms to see the ppt files structurally apart from just rendering it
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.
(Also, "Rust or native" is a strange dichotomy. What's not native about Rust?)
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.
...
For those that can't see the sarcasm: https://en.wikipedia.org/wiki/Godwin%27s_law
OH SHI~
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?
Perhaps it's time for you to become familiar with the terms of the Mozilla Public License, under which Libre Office is released.
Is this a MPL 2.0 violation?
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
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...
They bet on the online office suite (M365).
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
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.
But I have a license for the entire office 365 including Copilot premium.
Guess why?
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.
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
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 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.
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.
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.
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.
Maybe a used one?
https://www.apple.com/macbook-neo/ has it for ~$700
If there is anything that LLMs are rock solid at these days, it's unix terminal usage.
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.
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).
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?
If you don't like the Windows style of configuration, run powershell on linux - it's awesome there too!
I used to hate working in Windows, but now it feels roughly comparable to Mac (though at the risk of inciting an OS war, I do feel like Linux still beats both out...)
..like excuse me? Where the fuck else would we post feedback about it?
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.
It is the same with Claude Code. Each change they now lowers the harness' quality. Just yesterday they auto-updated it, and now backspace in the CLI does not work reliably. Pretty much all the regression I have experienced this year have also not been fixed.
https://x.com/bdsqlsz/status/2067964486615810369