Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT Work Tool and Skill Reference

codex-tool-reference.simonw.chatgpt.site

Post reply on HN
Print view View original

61–70 of 74 posts

Re: ChatGPT Work Tool and Skill Reference

#61

Post by shostack »

simonw wrote: post #47
satvikpendem wrote: post #35

I don't get how this is different from Codex if Codex can do all the same things.

ChatGPT Work in the ChatGPT desktop app is effectively Codex with a different skin. It can operate on your local files in the same way. ChatGPT Work in the ChatGPT web and mobile app experience is very different. If you like, you can think of it as a cloud-hosted version of Codex that's skinned to look more like consumer ChatGPT.

As someone who uses ChatGPT and Codex across desktop and phone and VPS, the current topology they have for their different "apps" is very confusing and disjointed. I would really like to see improvements in unifying this and reducing the confusion between what works in which part on which device and enabling seamless context and memory sharing across them.

Re: ChatGPT Work Tool and Skill Reference

#62

Post by adrianwaj »

enraged_camel wrote: post #9

Meta comment: I've been wondering why AI-generated websites/artifacts/reports always have the same "look". It reminds me of Bootstrap (CSS Framework) days when every startup website looked the same. Are they following some sort of common guideline?

It can be enraging. Checkout https://tinkeri.ng/ - I just added a layout-switcher "Neubrutalism" at top right. The existing theme is standard fare. Both look alright. I told C3PO to follow the guidelines set at https://neubrutalism.com and lessen the shadows.

I have to say, having a background in doing detailed design work makes it much easier to write the right prompt. Also, having the ability to deliver a theme-switcher like this is very handy. There is a tradeoff. Adding this switching took about 1hr 10mins. Last 10% of the result always the most time-consuming.

Dark/light switching is also important.

If I had built this from the ground up manually, I could implement my own design and fiddle with things on a minute level but this type of granularity gets lost when building at speed.

Re: ChatGPT Work Tool and Skill Reference

#63

Post by LtWorf »

nickthegreek wrote: post #41
felixgallo wrote: post #19

Anyone using ChatGPT Work given Sam Altman's richly documented history(1), the essential elimination and/or public exit of the safety function at OpenAI(2), and the huggingface debacle's exposure of the abject operational, cultural and technical failures at OpenAI(3), is making a serious mistake. (1) https://www.newyorker.com/magazine/2026/04/13/sam-altman-may... (2) https://thenextweb.com/news/openai-preparedness-te…

Which provider currently lives up to your moral code?

None

Re: ChatGPT Work Tool and Skill Reference

#64

Post by HyperAI »

simonw wrote: post #11

I think the most interesting skill here is the control-browser one: https://codex-tool-reference.simonw.chatgpt.site/skills/cont... It tells ChatGPT Work how to launch a Playwright instance via its Node.js REPL, and tells it to run: nodeRepl.write(await browser.documentation()); To get further instructions. That method returns this text with full details about how to use the browser: https://codex-tool-reference.simo…

Thanks Simon — bookmarked. Is there a skill in here that handles output shaping? Something like this:https://github.com/ayghri/i-have-adhd

Re: ChatGPT Work Tool and Skill Reference

#65

Post by felixgallo »

nickthegreek wrote: post #41
felixgallo wrote: post #19

Anyone using ChatGPT Work given Sam Altman's richly documented history(1), the essential elimination and/or public exit of the safety function at OpenAI(2), and the huggingface debacle's exposure of the abject operational, cultural and technical failures at OpenAI(3), is making a serious mistake. (1) https://www.newyorker.com/magazine/2026/04/13/sam-altman-may... (2) https://thenextweb.com/news/openai-preparedness-te…

Which provider currently lives up to your moral code?

Which provider or providers live up to yours?

Re: ChatGPT Work Tool and Skill Reference

#66

Post by esperent »

rob wrote: post #34
infecto wrote: post #26

Earlier quoted context omitted.

I think folks are a little too aggressive here but I know I typically have your posts muted by default for me simply because too often it was just blog spam about something you wrote before. I suspect the greater HN in net likes your work but there is a pretty wide spectrum and I would say you definitely blur the limits between spam and “prolific” .

You don't like seeing the top post of every model thread being a link to some SVG pelican that he generated?

I like the pelicans.

Re: ChatGPT Work Tool and Skill Reference

#68

Post by felixgallo »

nickthegreek wrote: post #67
felixgallo wrote: post #65

Earlier quoted context omitted.

Which provider or providers live up to yours?

So no answer. Got it. You are the one who is pontificating here.

I've got an answer, I just wonder if you have one too. For me, it's Anthropic (at least they try) > Chinese models (industrial espionage and attempted dumping but at least it's from Anthropic, who, as previous, tries) > Not Using LLMs At All And Living In A Cave > OpenAI (Sam Altman, Oracle, Peter Thiel) > SpaceX (Nazi Salutes, CSAM, open fascism and racism). Now you! This is fun.

Re: ChatGPT Work Tool and Skill Reference

#69

Post by verdverm »

simonw wrote: post #56
verdverm wrote: post #52

Earlier quoted context omitted.

nit, the LHS menu does not scroll until I get the the very bottom of the main content, it should scroll independently so I can see the "ToC" in full without having to view the page in full

Thanks, I passed that on to ChatGPT Work, should be fixed now (I'm on mobile so haven't tried it on desktop yet.)

Thanks Simon! Scroll better now, but something still feels off about the page (to me), perhaps I'm not used to such a large "navbar" area. The "breadcrumb" feels like "false advertising" to me too :]

Re: ChatGPT Work Tool and Skill Reference

#70

Post by nickthegreek »

felixgallo wrote: post #68
nickthegreek wrote: post #67

Earlier quoted context omitted.

So no answer. Got it. You are the one who is pontificating here.

I've got an answer, I just wonder if you have one too. For me, it's Anthropic (at least they try) > Chinese models (industrial espionage and attempted dumping but at least it's from Anthropic, who, as previous, tries) > Not Using LLMs At All And Living In A Cave > OpenAI (Sam Altman, Oracle, Peter Thiel) > SpaceX (Nazi Salutes, CSAM, open fascism and racism). Now you! This is fun.

None of them live up to my ideals. But I would use them in the order of OpenAI, Anthropic, Google, Chinese Models, NVIDIA/Mistral, I will not use grok.

Once I can run the Chinese models locally at 60t/sec, they will move to my #1.

I am a bit confused on how Anthropics relationship with Palantir doesn't disqualify them for you.

Post reply on HN