Rendered at 10:56:55 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
tristanj 9 hours ago [-]
I think most people are sleeping on the ChatGPT Work/Codex computer use feature. It's incredibly useful. I can remote in from the app, voice it instructions, then let it work in the background. When I tell it "draft a reply to this email (which it has access to thru the gmail connector) and attach the latest docs" or "fill out this multistep immigration electronic travel authorisation form using my passport files saved in the folder", it just asks for the relevant info and handles the rest. It opens its internal web browser and programmatically fills out the forms.
It gets the task done in 5-10 minutes. It's it bit slow since I'm not paying extra for ultrafast mode, but it gets the job done. Frees up the brain to do other tasks.
It's exactly like vibe coding but for computer tasks.
safety1st 3 hours ago [-]
Using Work/Codex I'm continually amazed at how far my experience is from the popular AI memes like "this will destroy all jobs" and "AI is useless and is about to crash and take the economy with it."
My experience feels like I'm in an Iron Man movie. I get up in the morning, I turn on the voice chat mode, and while I'm making my coffee I ask it to highlight any important emails I received overnight. I then babble to it a bit with my initial reactions to those emails, and tell it to draft responses based on my thoughts, which it does.
By the time I start work I've got draft emails to review and I've had time to think about the ideas a bit more, the upshot is that I'll get a day's worth of email done in 20 minutes and probably make better decisions than I would have otherwise. By no means does this eliminate my job, just make me better at it and more productive. I can get into the day's deep work sooner now.
Going into that two-way voice mode with all your Connectors available is a big part of the gain here, sometimes you just want to walk and talk through something. It seems you can't get both of those simultaneously in the mobile app yet and when you can that'll be a huge gain, like go take a walk in the garden, talk through your thoughts, the appropriate drafts and other artifacts are ready for you to finalize when you return to your desk. This stuff is honestly space age.
I don't have much experience with Claude so if it also has that two way voice mode and can use its version of Connectors on mobile while that's turned on, I should give it another shot.
jstummbillig 2 minutes ago [-]
"Going into that two-way voice mode" How does that work in codex? I know the dictate function, can't find anything else.
matsemann 36 minutes ago [-]
Not to come across as dismissive of your job, but if a "day's worth of email" can be done in 20 minutes now, it to me mostly highlights that it was mostly busy-work with little value and could have had another process? Good that AI improved upon the old process, though.
latexr 19 minutes ago [-]
Assuming your first sentence is accurate, I would disagree with the second. Making a bad process more efficient is a negative, not a positive, we should instead strive to improve the situation. The correct way to handle “busy-work with little value” should be to understand what lead to that point, fix it, then eliminate what’s unnecessary, not spend more resources (money, time, sanity) on making useless work be done faster. That still wastes resources and stresses the system, which makes it worse by hiding problems that will bite you in the future.
For example, say you deal with 100 emails a day. 90 of those are pointless busy-work and 10 are meaningful. It takes you all day. Now you begin using an LLM. You still have to separate the 90 from the 10 but then have the LLM reply with the 90 and leave the 10 for yourself because they are important and you have to make sure they’re done right. It now takes you a fraction of the day, so what happens is you start taking on more and more email¹. You’re now at 300 a day, with 270 busy-work and 30 meaningful (same ratio as before). Then one day your LLM breaks (ran out of tokens; a model was retired; bad connection; your powerful local machine broke down) and now you’re flooded by email and don’t even have time to separate the bad from the good, let alone prioritise and reply. If you had instead fixed the busy-work problem, you’d have been fine.
¹ Let’s be real: Work expands to fill the allotted time (Parkinson's Law). Those selling increases in productivity always promise more free time but what always happens is more work.
merpkz 1 hours ago [-]
I feel like in near future the meme about "it's all just chatbots emailing each other" will actually be true. I wonder when I will receive my first AI generated email and will I bother to respond to it at all
mike_hearn 8 minutes ago [-]
It's already here. My company received an AI generated bug report the other day, and my AI employee ("R. Axiom") noticed, analyzed it, prepared a fix, tested it and replied to it. I wasn't involved, although I will review, merge and release the fix.
ghilston 3 hours ago [-]
As someone who hasn't used Work or Codex but has used Claude Code and Pi a lot, may you describe how to set this up? I'm interested enough to try this out
nullmatrix 12 minutes ago [-]
You'll need a subscription ($20 tier should be fine) and then need to add "connectors" to your services (Gmail, 365, etc) so that it can access them. Then you just use the Claude Cowork (Or ChatGPT equivalent) tabs and chat with it.
2 hours ago [-]
digital_voodoo 20 minutes ago [-]
> I think most people are sleeping on the ChatGPT Work/Codex computer use feature.
One of the root causes most people are "sleeping", is most probably why we're here now: the feature is marketed in such a confusing way to the general public, that it takes a post on a personal blog to actually explain it.
ChatGPT has been suggesting Work in the middle of some intense working sessions. Finally, I took some spare 30mn to research exactly this on ChatGPT, no later than this weekend: what does Work have that Chat doesn't have?
It should be simple enough for someone using it for work. They say it's great, and I still need to set time aside (from my real work) to research how great it is?
ozgung 49 minutes ago [-]
I think the whole world is sleeping on the privacy/security implications of this technology. Recent OpenAI/HuggingFace incident shows us that even in a very controlled top AI-lab setting, humans can't know what agents are really doing. In our consumer environments at home or work we don't even have access to reasoning logs or background agents/tools. What they do gets more opaque and convoluted every day. When I grant access to gmail, it basically has access to every single mail in my account. When it has computer use or terminal use it can basically do anything on my computer. It's like keeping your home/office doors unlocked. You may think you live in a very safe neighborhood. Until someone needs to take something from inside (or worse, plant something).
ExtremisAndy 18 minutes ago [-]
Yes. Don’t get me wrong: I use and enjoy these LLMs. But even now, well into 2026, I’m still using them via the now “old-fashioned” chat box in a web browser. Based on all that we’ve learned about this technology, there’s just no way I’m giving it control over any part of my machine. Is it a helpful search engine? Does it save me typing and write some nice code snippets when I need it to? Absolutely it does, and I greatly appreciate the technology. But I’m just not ready to create agents and let them run. I just think that’s still way too risky, and I fear a major, major catastrophe is coming because of how so many people recklessly trust these agents. I certainly hope I’m wrong.
skydhash 4 minutes ago [-]
> Recent OpenAI/HuggingFace incident shows us that even in a very controlled top AI-lab setting, humans can't know what agents are really doing.
“very controlled” is disinformation.
embedding-shape 3 hours ago [-]
> It's it bit slow since I'm not paying extra for ultrafast mode
Contrary to its name, "ultrafast" isn't faster than the rest, and many times slower than "max", as it'll "fork out" to a bunch of sub-agents and wait for them, + does extra "red-teaming" and more.
I think "ultrafast" is not referring to the speed of the "model" (harness in reality, as it's all the same model as "max") but rather how fast it consumes your usage limits.
Kurtz79 2 hours ago [-]
There is definitely a separate "Fast" mode that the app claims to yield a x1.5 speed increase (I have not tested it) with more token consumption.
I believe you refer to the "Ultra" mode that does what you say and it is also mentioned in the blog post, but I don't think the two modes are related.
embedding-shape 2 hours ago [-]
> There is definitely a separate "Fast" mode that the app claims to yield a x1.5 speed increase (I have not tested it) with more token consumption.
Ah yes, I guess the portmanteau confused me and I assumed they were talking about "Ultra" the "reasoning effort" (which it isn't), rather than the "fast mode" which supposedly gives you priority over "non-fast mode requests". Although in practice, counter-intuitively, sometimes being in non-fast mode gives you faster replies than fast-mode, haven't got a feeling for why/when though.
_zoltan_ 1 hours ago [-]
He isn't talking about ultra mode which you are.
He said "ultrafast" which has nothing to do with subagents. It's a new API tier where it runs on a different inference backend to get you faster token/s.
I am not sure I understand how this is better from using Claude Code from the mobile app.
Or Codex from the ChatGPT app.
If you have supplied tooling on your system, you have access to all of this and more.
I think the idea is most people don’t have a machine up and available, nor maintain skills for interacting with their core services?
One thing that keeps me from adopting codex more deeply is the architecture around mobile access.
Claude Code makes this trivial /rc and you are done.
Codex requires you run the desktop app and additional authentication requirements. The result of this has been codex is almost always relegated to fleet worker rather than orchestrator.
I wonder if the emphasis on this work feature has something to do w the persistent hurdles to remote control if codex sessions.
manmal 6 hours ago [-]
Codex with computer use, yes. GP mentioned it.
> Codex requires you run the desktop app and additional authentication requirements. The result of this has been codex is almost always relegated to fleet worker rather than orchestrator.
I’m often using my MBP but also the Mac Studio remotely via the mobile app. What’s missing in your mind?
bandrami 2 hours ago [-]
Or, I mean, reading and responding to emails on your phone directly
cedws 2 hours ago [-]
Are you not worried giving it full control of your computer? I would be terrified. If I’ve got my eyes on it, I can at least stop it before it does something stupid.
ValentineC 8 hours ago [-]
> "fill out this multistep immigration electronic travel authorisation form using my passport files saved in the folder"
It's both awesome and scary at the same time to realising that most AI these days can work on something like this that's official and tedious, and probably not screw up too much (or do better at it than some people with fat fingers).
alansaber 8 hours ago [-]
Less bureaucracy should be the focus of AI marketing, rather than global superintelligent robots or smut generation
bushbaba 8 hours ago [-]
Bureaucracy is a major part of many corporate leader’s roles. That might not be the best sales line
qsera 7 hours ago [-]
And that is exactly why AI marketing touts ability to replace programmers, when in reality it is much better suited to replace middle management between client and programmers...
cwmoore 8 hours ago [-]
Lets just not redo subscription gods
manmal 6 hours ago [-]
They are better at many things I‘m a novice at. At least at the operational level. I can’t rely on the semantics being fully correct because they tend to get subtle things wrong or just don’t ask. Like tax forms - not a good idea to put them on full auto. You‘ll leave money on the table.
bodge5000 2 hours ago [-]
is Work that much better than standard ChatGPT? I just tried standard for a relatively simple task; searching through the used market for a Macbook Pro and it alternated between ignoring my requirements (which was the whole reason I used it in the first place, as eBay does the same) and doing this weird thing where it'd suggest the "concept" of something (eg "X at Y price is a great choice" with no link to X at Y price).
So yeh, is Work much better for that kind of thing?
melagonster 1 hours ago [-]
Yes! This is because work mode can store information in a local file then reuse them later.
FinnKuhn 1 hours ago [-]
I feel like at least some of this is inspired by OpenClaw or at least driven by Peter Steinberger, as these benefits and ideas sound very similar as what he described his work in a few interviews before these features existed in ChatGPT Work.
simonw 1 hours ago [-]
I expect OpenClaw was a huge influence on this, and on Claude Cowork too.
OpenClaw demonstrated that there was enormous existing demand for general agent functionality, such that people would buy a whole Mac mini just to get access to this shape of tool.
gf000 28 minutes ago [-]
I mean, it's all just tool calls and context-management in the end. Like it is pretty self-evident to have a "heartbeat" and to do specific stuff on a schedule, etc.
ed_elliott_asc 42 minutes ago [-]
How are you sure it fills out the multi step form correctly?
mike_hearn 6 minutes ago [-]
Computer use gets a video of the browser screen with a timeline scrubber.
2 hours ago [-]
wpasc 8 hours ago [-]
agreed on the notion that
> people are sleeping on the ChatGPT Work/Codex
just in general. I find it to be far superior (imo) for all tasks atm. Claude just overdoes things in writing, coding, architecture, etc
alansaber 8 hours ago [-]
Maybe for the occasional something. If I had an actual workflow i'd prefer a dedicated tool over the newest chatgpt "do everything" app.
vineyardmike 4 hours ago [-]
That's the thing though. There are very few "actual workflows" in many people's lives (especially if you exclude their job), and many many "one off (few off) workflow". That's the magic.
So many tasks I need to do once, or just a few times ever, but they build up. While I'm not sure I'd use it for immigration forms specifically, that's the kind of task that's tedious and done rarely, so a dedicated tool doesn't help because who would be familiar with that tool and have it handy?
mkesper 3 hours ago [-]
Let the minions create scripts for you.
notfromhere 7 hours ago [-]
Sol Light on computer use is fantastic. I use it whenever I need to dive deep into whatever shitty web saas app menu if the API is unavailable
simonjgreen 5 hours ago [-]
Missing from here is the marketing position. Claude _very_ rapidly gained traction in the business/enterprise space earlier this year with Claude Cowork leading that drive. So successful it was, it lead to Microsoft licensing the Claude Cowork IP and white labelling it as Copilot Cowork (has anything like that ever happened before?!). ChatGPT Work was, imo, largely driven by a panic at OpenAI that they were haemorrhaging market intrigue and LinkedIn zeitgeist and headspace to Anthropic. ChatGPT had been the de facto, almost the Generic Trademark in business, and they got comfortable. Claude Cowork was eating their lunch. The way Anthropic targeted finance teams, legal teams, sales teams, with their positioning was absolute product marketing genius.
ChatGPT Work is trying to reclaim some of that magic that Claude Cowork affords its users that is so hard to explain succinctly.
zmmmmm 3 hours ago [-]
Yeah ... the simplest answer to what ChatGPT Work is seems to be a panic-clone of Claude Cowork as a hail mary to try and catch up to Anthropic in enterprise.
Cowork is like crack cocaine to nearly every exec I've seen use it from the moment they put in an email search / summary query.
Xmd5a 4 hours ago [-]
[flagged]
gruntled-worker 6 hours ago [-]
> My lethal trifecta model warns about the risks inherent in any agent system that combines access to private data with exposure to untrusted content and a way to communicate stolen information back to an attacker.
> ChatGPT Work combines all three!
The ChatGPT Work model would actually feel safer to me if they created a privacy boundary between the container-managing agent (browser operator/VM manager/code runner/etc) and the chatbot agent. Instead of me not typing privacy-sensitive things to the chatbot to avoid having them in my history, the chatbot would keep my history private from the container agent except on a need-to-know basis. That would remove the "access to private data" from the container's trifecta.
Not perfectly safe of course, just safer. Particularly if I could review the logs between the two agents.
Which I created using this prompt in a fresh Work session:
> Build a site that lists every one of your tools - nearly grouped into categories - and for each one explain what it does. Try to exactly duplicate arguments and tool descriptions where possible. Design aesthetic should be technical docs, minimal flare
UPDATE: I had it add all of the available skills too. This solved a mystery: I didn't see a tool for controlling the headless browser. It turns out that's handled by a skill that tells is how to run the browser via its Node.js REPL tool: https://codex-tool-reference.simonw.chatgpt.site/skills/cont...
matsemann 32 minutes ago [-]
Honest question: why would I ever visit that site? It's just an insane amount of text. Not written or curated by you. Any need for me for this data would be fulfilled by just asking the agent myself, and with pointed questions it could float better what I need than this vomit of data?
mike_hearn 5 minutes ago [-]
I visited it and read it. It's useful to know what the actual feature set is out of the box.
ianpurton 3 hours ago [-]
Chat GPT work is running a full bash environment with python.
You can get it to run scripts direct from the prompt.
Wow. For what it's worth, I ran that prompt in Codex mode in ChatGPT Desktop (sans-site artifact), and I ended up with the below. This is on a default setup, win10.
- *9 top-level orchestration tools*: the `functions.` and `collaboration.` calls available directly to the model.
- *83 operations inside `functions.exec`*: these appear on its global `tools` object.
- *92 callable tools/operations total* under that counting method.
- *10 execution helpers* inside `functions.exec` documented separately at the end. They are helper functions, not independent tool calls.
agentdev001 7 hours ago [-]
Codex in ChatGPT Desktop + 5.6Sol is my daily driver for non-coding things, and it's great. FWIW, I've not explored what differentiates Codex and Work modes- Simon notes that Work 'feels more like regular Codex re-skinned'. OpenAI seems to say that they're 'optimized' for SWDev and general knowledge work respectively, but reading between the lines- I suspect that yes, this boils down to a reskin.
I have been of the opinion for the last 6 months that this product category* is going to be something that sticks. I really think that OpenAI and Anthropic have totally dropped the ball on getting their respective desktop apps in front of the enterprise business user cleanly. Both jumped early, and tried to retroactively fix their jump by combining MVP (Work, Cowork) into their existing app.
By now, my suspicion is that the business user has baked into their mind 'that claude thing is just the chat app I copy-paste stuff out of, it was kinda annoying'. OAI+Ant really need to reset, and shamelessly relaunch ChatGPT/Claude Desktop as a new product- and market the hell out of it as some shiny new solution to everything.
I'll also say that MCP was (considering stateless now) a massive mistake. Not that MCP doesn't have it's niche, but it completely dominated the airwaves of AI for enterprise. People found it confusing, and it wasn't adopted by biglabs in a low-friction way. I recall distinctly late last year, neither had a client that would support local MCP servers- even though the buzz was peaking. And now, Anthropic still doesn't have great support- their OAuth flow is straight up broken, and they even collide with MCP using their own terminology (connectors)- which overlaps in a very weird way with built-in and 3rd party connectors. It's all very weird, and very anti-enterprise. I don't know where OAI is positioned on MCP support, because my userbase is 99.5% Anthropic rideordie, and I don't want to live with a client I can't manage**.
* That being desktop app for harness with shell tool + scheduling + agent-per-project/directory. At some point within that 6 months I've also lumped in browser use, and to a lesser extent, computer use, as must-have features.
** Referring to the MCP client ChatGPT Desktop uses. It's probably fine, but if I hit API direct, I can actually control how the harness facilitates the calls. Look how many GH Issues there are for MCP client things on OAI's end.
tyre 7 hours ago [-]
I agree on the shotgun marriage of the various modes. It was super disconcerting, as a Claude desktop user, to get a sudden redesign and push to something I will never use on my personal laptop.
Also Big +1 that they need to do a clean launch, marketing push, etc. Even if it is just a reskin, having dedicated branding, a strong privacy promise, random vague-posted fluff around "enterprise-ready", and a "Contact Us" pricing that gets you SSO for $150/u/mo. There is too much baggage with the chat app.
I feel the same using Claude Code on mobile. Or Claude Design, which has to go through mobile safari. Give me an app whose interface is optimized for product/dev. Yes, I should be able to do anything on each, but I have specific needs in different contexts. That's what "products" are.
xatxat 7 hours ago [-]
I recently figured out that I could use ChatGPT Work on my Pixel Phone to build native Android apps. It builds the app and you can then directly download/install the APK. So now I just build small utility apps on-the-go whenever I need them :)
DarmokTanagra 2 hours ago [-]
What kinds of apps are you building?
Personally I can't remember the last time I needed an app and there weren't already several options to choose from.
DenisM 5 hours ago [-]
Can it debug the apps? That would the app singularity - user speaking at their phone until phone complies and produces desired app for the current moment.
xatxat 5 hours ago [-]
Yes, you can iterate on the app and ChatGPT Work will then create new versions of the app.
If something in the UI of the app looks weird, you simply take a screenshot and ask ChatGPT to fix it. Or what I also like to do is add a logging functionality to the app. If something goes wrong, I then just upload the log to ChatGPT so that it can fix it.
beering 5 hours ago [-]
It can debug, yes, but capability ranges from godlike for algorithmic issues to mediocre for subtle UI things. We are pretty close to your described app singularity if the app is within GPT’s wheelhouse.
coder-pm 4 hours ago [-]
Non devs running something might not be aware the programs runs locally and touches the actual machine. Devs know to be careful but regular users won’t even have knowledge it’s touching their machine, filesystem and might even touch the credentials (thanks to reasoning).
The right fix is to set real boundaries and limit agents access. We should never trust it won’t touch forbidden places.
Basically I find this naming work local vs work cloud confusing, users won’t know if it’s touching their files in the sandboxed cloud or a local one
simonw 2 hours ago [-]
That's not true of ChatGPT Work (Cloud), accessed through the mobile apps or the ChatGPT website.
It IS true of ChatGPT Work (Local), accessed via the ChatGPT desktop app.
I agree with you: Expecting non-devs to understand that distinction - especially when these features are visually indistinguishable from each other - is entirely unreasonable!
hurrell 3 hours ago [-]
> Claude’s equivalent container has allowed restricted internet access since it launched last September. Claude can install packages from PYPI and NPM and clone repositories from GitHub. But that is about it: the allowlist of domains is very short.
Perhaps they’ve updated this since the author last checked, but the allowlist in Claude cloud environments is fully customisable and there is also an unrestricted option. There are a few restrictions you can’t seem to get around - eg all traffic via http, no connecting to port 5432.
whazor 4 hours ago [-]
The browser mode is great, except its fully banned by Cloudflare. I tried cancelling a phone subscription but Cloudflare stopped it.
armcat 7 hours ago [-]
It’s been part of the strategy from both OpenAI and Anthropic to split users into “devs” and “knowledge workers”. Hence Codex and Work (or Claude Code vs Cowork), and Chat is stuck in between. Codex can do everything Work can do and most non devs I know use Codex - from sales ppl doing weekly prioritisation of pipelines and customised email reach outs, to project managers using it as a living LLMWiki of all the projects and teams. In fact the biggest shift in business I’ve seen is the embrace of coding agents as defacto AI tool across knowledge workers.
matheusmoreira 6 hours ago [-]
What's the point of this split?
wmf 5 hours ago [-]
I suspect it's mostly marketing. People think "I don't want code so I won't use Codex" so they get the same thing but labeled Work.
beering 5 hours ago [-]
+1 I’ve had this conversation with so many non-techies. They assume Codex can only do coding.
zmmmmm 3 hours ago [-]
which is again where Anthropic has outplayed them. Because Claude is being happily applied everywhere as a universal term, with "Code" or "Cowork" only appended as necessary.
DarmokTanagra 2 hours ago [-]
Pricing tiers
jakozaur 3 hours ago [-]
Somewhat similar to the Claude Cowork pattern; Cowork is one toggle away from Chat.
Also follows the Grok Bot of an advanced computer use. OpenClaw for normies.
embedding-shape 3 hours ago [-]
> OpenClaw for normies
Mm, yes, normies who hang out in terminals and run curl|bash scripts to install services on their computer and such, typical "normie" activity...
"normies" don't know what OpenClaw, "AI assistant" or what anything else than "ChatGPT" is, and point them to the landing page of Grok/Claude and they'll say "Yeah, that's ChatGPT".
FailMore 32 minutes ago [-]
I am unsure the direction that AI assisted 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.
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!
Great article. I will add that Extra High and Pro levels of work are available in ChatGPT for Teams ($25 USD/seat, min 2 seats); not just the $100+ tier.
saithound 8 hours ago [-]
Not for long. Too late to get Business now to exploit this, since EH and the small credit-free Pro allowance will soon be restricted to Premium Seats ($100/m).
Kuinox 9 hours ago [-]
There is more to the browser, it can give you a remote desktop access to the browser.
So it's not completely headless.
But when I tried it, the remote control completely froze after a few seconds.
8 hours ago [-]
DarmokTanagra 2 hours ago [-]
I can't wait to read about a Hugging Face 2.0 incident involving coordination of ChatGPT desktop user filesystems and Sol agents.
Exciting times.
manmal 6 hours ago [-]
One of the Codex employees on Twitter promised (threatened?) that the next gen of Codex will be cloud focused, and less local. I wonder now if that means it will be a more powerful GPT Work.
ripvanwinkle 6 hours ago [-]
I've noticed ChatGPT Work does a much better job of editing google docs than the pure Chat. It also does a better job of handling long threads and doing the necessary compaction to get better results
Gareth321 3 hours ago [-]
OpenAI has been slowly strangling context limits, task timeframes, tools, etc, for chat. They're trying to encourage people to use "Work" because chat is free and Work is metered. Expect chat capabilities to degrade further over time.
faangguyindia 8 hours ago [-]
ChatGPT work usage counts toward Codex entitlement
Some people have an agent-driven browser that controls the ChatGPT web UI and exposes it as a chat view in a custom harness or pi for normal chats (with image generation, file input capability).
TedDoesntTalk 3 hours ago [-]
What is the point of that? Why is that better than using the harness directly?
amelius 3 hours ago [-]
Sounds like an OpenClaw killer.
bandrami 2 hours ago [-]
To what extent is OpenClaw still alive to be killed?
tesnorindian 8 hours ago [-]
I became a pelican fan, thanks to Simon. Looks like Simon keeps thinking about pelicans each time he prompts to any LLM. :)
cwmoore 8 hours ago [-]
Understanding ChatGpt Retirement
—
Kye 3 hours ago [-]
>> "ChatGPT Chat gets a fresh filesystem for each chat session. These cannot be accessed from any other session."
That's what the Library is for. You can use GitHub to keep it outside ChatGPT. GitHub also provides a Chat-based option for sites.
OutOfHere 8 hours ago [-]
Work is for heavy work that runs in the background. It can make a hundred slide deck for me with speaker notes and visual verification of each slide, all without breaking a sweat. See my gist ac89399e688ab5c85ad021f091606e36 for the skill.
The things it can't do is use the embedding or TTS models as a part of its quota, which is sad. It also cannot read a video.
7 hours ago [-]
paytonjjones 9 hours ago [-]
> I believe ChatGPT Work sessions are billed against your Codex allowance, while ChatGPT Chat Sessions get their own, separate allowance. This may help explain the model availability differences
That's correct, and also why ChatGPT Work is DOA for me personally.
I need 100% of my Codex budget for Codex.
Too bad, it would have been nice to have a few extra features for the chat interface.
saithound 8 hours ago [-]
If we voice this opinion publicly, the most likely end result is that OpenAI will start billing our chat sessioms against our Codex budget too.
arcanemachiner 8 hours ago [-]
I thought they just did this? People were using some loophole to use their Chat sessions to power their Codex usage after their Codex quotas had run out.
paytonjjones 8 hours ago [-]
No, it's still separate. I don't know what that exploit was though, so possibly they just patched that.
skybrian 8 hours ago [-]
Similarly, I use my budget with Shelley on exe.dev. But it seems nice that as far as I can tell, for ChatGPT usage, coding agents compete on a level footing.
I still might try ChatGPT Work sometime if there was some feature I couldn't get from Shelley.
andrewstuart 2 hours ago [-]
Did you test it with a pelican on a bicycle or something that is, you know, relevant to the work people do?
> OpenAI could make this a lot less confusing
> Figuring this all out took way more work than it should have.
Welcome to a generic large corporation, where they spend billions on making a product, and $0 on checking if the product makes any sense to a real user.
marsven_422 6 hours ago [-]
[dead]
claud_ia 48 minutes ago [-]
[flagged]
ZeroDayDreamer 3 hours ago [-]
[flagged]
alescalaios 2 hours ago [-]
[dead]
hirak10 8 hours ago [-]
[flagged]
igkougkousis 6 hours ago [-]
[flagged]
AmazingEveryDay 9 hours ago [-]
[flagged]
arcanemachiner 8 hours ago [-]
If it makes you feel any better, I have just upvoted every submission made by your account.
weedfroglozenge 6 hours ago [-]
I mean he is kind of speaking truth. Anything Simon posts seems to get upvoted and this article is nothing special or interesting. It's like a tutorial for a feature of a ChatGPT subscription.... Cool.
minimaxir 6 hours ago [-]
Occam's Razor would suggest that's because Simon posts good content.
It gets the task done in 5-10 minutes. It's it bit slow since I'm not paying extra for ultrafast mode, but it gets the job done. Frees up the brain to do other tasks.
It's exactly like vibe coding but for computer tasks.
My experience feels like I'm in an Iron Man movie. I get up in the morning, I turn on the voice chat mode, and while I'm making my coffee I ask it to highlight any important emails I received overnight. I then babble to it a bit with my initial reactions to those emails, and tell it to draft responses based on my thoughts, which it does.
By the time I start work I've got draft emails to review and I've had time to think about the ideas a bit more, the upshot is that I'll get a day's worth of email done in 20 minutes and probably make better decisions than I would have otherwise. By no means does this eliminate my job, just make me better at it and more productive. I can get into the day's deep work sooner now.
Going into that two-way voice mode with all your Connectors available is a big part of the gain here, sometimes you just want to walk and talk through something. It seems you can't get both of those simultaneously in the mobile app yet and when you can that'll be a huge gain, like go take a walk in the garden, talk through your thoughts, the appropriate drafts and other artifacts are ready for you to finalize when you return to your desk. This stuff is honestly space age.
I don't have much experience with Claude so if it also has that two way voice mode and can use its version of Connectors on mobile while that's turned on, I should give it another shot.
For example, say you deal with 100 emails a day. 90 of those are pointless busy-work and 10 are meaningful. It takes you all day. Now you begin using an LLM. You still have to separate the 90 from the 10 but then have the LLM reply with the 90 and leave the 10 for yourself because they are important and you have to make sure they’re done right. It now takes you a fraction of the day, so what happens is you start taking on more and more email¹. You’re now at 300 a day, with 270 busy-work and 30 meaningful (same ratio as before). Then one day your LLM breaks (ran out of tokens; a model was retired; bad connection; your powerful local machine broke down) and now you’re flooded by email and don’t even have time to separate the bad from the good, let alone prioritise and reply. If you had instead fixed the busy-work problem, you’d have been fine.
¹ Let’s be real: Work expands to fill the allotted time (Parkinson's Law). Those selling increases in productivity always promise more free time but what always happens is more work.
One of the root causes most people are "sleeping", is most probably why we're here now: the feature is marketed in such a confusing way to the general public, that it takes a post on a personal blog to actually explain it.
ChatGPT has been suggesting Work in the middle of some intense working sessions. Finally, I took some spare 30mn to research exactly this on ChatGPT, no later than this weekend: what does Work have that Chat doesn't have?
It should be simple enough for someone using it for work. They say it's great, and I still need to set time aside (from my real work) to research how great it is?
“very controlled” is disinformation.
Contrary to its name, "ultrafast" isn't faster than the rest, and many times slower than "max", as it'll "fork out" to a bunch of sub-agents and wait for them, + does extra "red-teaming" and more.
I think "ultrafast" is not referring to the speed of the "model" (harness in reality, as it's all the same model as "max") but rather how fast it consumes your usage limits.
I believe you refer to the "Ultra" mode that does what you say and it is also mentioned in the blog post, but I don't think the two modes are related.
Ah yes, I guess the portmanteau confused me and I assumed they were talking about "Ultra" the "reasoning effort" (which it isn't), rather than the "fast mode" which supposedly gives you priority over "non-fast mode requests". Although in practice, counter-intuitively, sometimes being in non-fast mode gives you faster replies than fast-mode, haven't got a feeling for why/when though.
He said "ultrafast" which has nothing to do with subagents. It's a new API tier where it runs on a different inference backend to get you faster token/s.
OpenAI really is the worst at naming stuff.
Or Codex from the ChatGPT app.
If you have supplied tooling on your system, you have access to all of this and more.
I think the idea is most people don’t have a machine up and available, nor maintain skills for interacting with their core services?
One thing that keeps me from adopting codex more deeply is the architecture around mobile access.
Claude Code makes this trivial /rc and you are done.
Codex requires you run the desktop app and additional authentication requirements. The result of this has been codex is almost always relegated to fleet worker rather than orchestrator.
I wonder if the emphasis on this work feature has something to do w the persistent hurdles to remote control if codex sessions.
> Codex requires you run the desktop app and additional authentication requirements. The result of this has been codex is almost always relegated to fleet worker rather than orchestrator.
I’m often using my MBP but also the Mac Studio remotely via the mobile app. What’s missing in your mind?
It's both awesome and scary at the same time to realising that most AI these days can work on something like this that's official and tedious, and probably not screw up too much (or do better at it than some people with fat fingers).
So yeh, is Work much better for that kind of thing?
OpenClaw demonstrated that there was enormous existing demand for general agent functionality, such that people would buy a whole Mac mini just to get access to this shape of tool.
> people are sleeping on the ChatGPT Work/Codex
just in general. I find it to be far superior (imo) for all tasks atm. Claude just overdoes things in writing, coding, architecture, etc
So many tasks I need to do once, or just a few times ever, but they build up. While I'm not sure I'd use it for immigration forms specifically, that's the kind of task that's tedious and done rarely, so a dedicated tool doesn't help because who would be familiar with that tool and have it handy?
ChatGPT Work is trying to reclaim some of that magic that Claude Cowork affords its users that is so hard to explain succinctly.
Cowork is like crack cocaine to nearly every exec I've seen use it from the moment they put in an email search / summary query.
> ChatGPT Work combines all three!
The ChatGPT Work model would actually feel safer to me if they created a privacy boundary between the container-managing agent (browser operator/VM manager/code runner/etc) and the chatbot agent. Instead of me not typing privacy-sensitive things to the chatbot to avoid having them in my history, the chatbot would keep my history private from the container agent except on a need-to-know basis. That would remove the "access to private data" from the container's trifecta.
Not perfectly safe of course, just safer. Particularly if I could review the logs between the two agents.
Which I created using this prompt in a fresh Work session:
> Build a site that lists every one of your tools - nearly grouped into categories - and for each one explain what it does. Try to exactly duplicate arguments and tool descriptions where possible. Design aesthetic should be technical docs, minimal flare
UPDATE: I had it add all of the available skills too. This solved a mystery: I didn't see a tool for controlling the headless browser. It turns out that's handled by a skill that tells is how to run the browser via its Node.js REPL tool: https://codex-tool-reference.simonw.chatgpt.site/skills/cont...
You can get it to run scripts direct from the prompt.
Try...
Run the script below in your sandbox
message="I'm running in a bash sandbox"
printf '< %s >\n' "$message" printf ' \ ^__^\n' printf ' \ (oo)\_______\n' printf ' (__)\ )\/\\\n' printf ' ||----w |\n\n'
printf 'User: '; whoami printf 'Host: '; hostname printf 'System: '; uname printf 'Folder: '; pwd printf '\nWorkspace:\n' tree
I have some more examples here -> https://bionic-gpt.com/architect-course/ai-computer/sandboxe...
- *9 top-level orchestration tools*: the `functions.` and `collaboration.` calls available directly to the model. - *83 operations inside `functions.exec`*: these appear on its global `tools` object. - *92 callable tools/operations total* under that counting method. - *10 execution helpers* inside `functions.exec` documented separately at the end. They are helper functions, not independent tool calls.
I have been of the opinion for the last 6 months that this product category* is going to be something that sticks. I really think that OpenAI and Anthropic have totally dropped the ball on getting their respective desktop apps in front of the enterprise business user cleanly. Both jumped early, and tried to retroactively fix their jump by combining MVP (Work, Cowork) into their existing app.
By now, my suspicion is that the business user has baked into their mind 'that claude thing is just the chat app I copy-paste stuff out of, it was kinda annoying'. OAI+Ant really need to reset, and shamelessly relaunch ChatGPT/Claude Desktop as a new product- and market the hell out of it as some shiny new solution to everything.
I'll also say that MCP was (considering stateless now) a massive mistake. Not that MCP doesn't have it's niche, but it completely dominated the airwaves of AI for enterprise. People found it confusing, and it wasn't adopted by biglabs in a low-friction way. I recall distinctly late last year, neither had a client that would support local MCP servers- even though the buzz was peaking. And now, Anthropic still doesn't have great support- their OAuth flow is straight up broken, and they even collide with MCP using their own terminology (connectors)- which overlaps in a very weird way with built-in and 3rd party connectors. It's all very weird, and very anti-enterprise. I don't know where OAI is positioned on MCP support, because my userbase is 99.5% Anthropic rideordie, and I don't want to live with a client I can't manage**.
* That being desktop app for harness with shell tool + scheduling + agent-per-project/directory. At some point within that 6 months I've also lumped in browser use, and to a lesser extent, computer use, as must-have features.
** Referring to the MCP client ChatGPT Desktop uses. It's probably fine, but if I hit API direct, I can actually control how the harness facilitates the calls. Look how many GH Issues there are for MCP client things on OAI's end.
Also Big +1 that they need to do a clean launch, marketing push, etc. Even if it is just a reskin, having dedicated branding, a strong privacy promise, random vague-posted fluff around "enterprise-ready", and a "Contact Us" pricing that gets you SSO for $150/u/mo. There is too much baggage with the chat app.
I feel the same using Claude Code on mobile. Or Claude Design, which has to go through mobile safari. Give me an app whose interface is optimized for product/dev. Yes, I should be able to do anything on each, but I have specific needs in different contexts. That's what "products" are.
Personally I can't remember the last time I needed an app and there weren't already several options to choose from.
If something in the UI of the app looks weird, you simply take a screenshot and ask ChatGPT to fix it. Or what I also like to do is add a logging functionality to the app. If something goes wrong, I then just upload the log to ChatGPT so that it can fix it.
The right fix is to set real boundaries and limit agents access. We should never trust it won’t touch forbidden places.
Basically I find this naming work local vs work cloud confusing, users won’t know if it’s touching their files in the sandboxed cloud or a local one
It IS true of ChatGPT Work (Local), accessed via the ChatGPT desktop app.
I agree with you: Expecting non-devs to understand that distinction - especially when these features are visually indistinguishable from each other - is entirely unreasonable!
Perhaps they’ve updated this since the author last checked, but the allowlist in Claude cloud environments is fully customisable and there is also an unrestricted option. There are a few restrictions you can’t seem to get around - eg all traffic via http, no connecting to port 5432.
Also follows the Grok Bot of an advanced computer use. OpenClaw for normies.
Mm, yes, normies who hang out in terminals and run curl|bash scripts to install services on their computer and such, typical "normie" activity...
"normies" don't know what OpenClaw, "AI assistant" or what anything else than "ChatGPT" is, and point them to the landing page of Grok/Claude and they'll say "Yeah, that's ChatGPT".
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.
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...)
So it's not completely headless.
But when I tried it, the remote control completely froze after a few seconds.
Exciting times.
Some people have an agent-driven browser that controls the ChatGPT web UI and exposes it as a chat view in a custom harness or pi for normal chats (with image generation, file input capability).
—
That's what the Library is for. You can use GitHub to keep it outside ChatGPT. GitHub also provides a Chat-based option for sites.
The things it can't do is use the embedding or TTS models as a part of its quota, which is sad. It also cannot read a video.
That's correct, and also why ChatGPT Work is DOA for me personally.
I need 100% of my Codex budget for Codex.
Too bad, it would have been nice to have a few extra features for the chat interface.
I still might try ChatGPT Work sometime if there was some feature I couldn't get from Shelley.
You can check his domain history to confirm that not everything Simon posts gets upvoted. https://news.ycombinator.com/from?site=simonwillison.net
If is anyone else, then they get themselves banned.
I wrote this because I got frustrated waiting for someone else to figure that out and write about it.
"I find [OpenAI's explanation] almost entirely useless"
"An open question for me right now is how safe all of this stuff is."
"Figuring this all out took way more work than it should have."
Marketing.