I've used a similar technique with my own tools. It helps to save context overall, by deferring the detailed instructions not only to when they're needed, but also to where they're needed.
Simply loading the browser Skill alone, doesn't always mean a browser is actually necessary (or supported). The user might've want them to control their main desktop browser; or the user might be pointing them toward a read-only HTML file that doesn't need rendering; or the sandbox might prevent network access; etc...
Codex is especially 'keen' to use Skills (especially by comparison to Claude), I often see it load Skills which it doesn't go on to use, because the main Skill content says "when not to use this". So I'm sure this is a product design decision to help with those kinds of circumstances.
It's runtime dependent on the browser being used! A skill file wouldn't be able to have this dynamically injected for the browser that's about to be used.
Skill file could indicate general instructions for all browsers. This provides guidance for the browser that's about to actually be used.
Simon, thanks for all the great work you do. I definitely appreciate your contributions to discussion threads here as well as your blog. I learned so much from you.
simonw is one of the finest contributors to HN and we're lucky to have him.
I realize that for some people there is too much LLM-related content and (therefore?) too much by certain authors, but that has always been the case for certain topics and certain authors in HN's history. This is a side effect of the frontpage being the same for everyone, and therefore the scarcest resource.
My comment here is entirely justified in this case.
Someone else submitted my vibe-coded slop site to the front page without any context, and it accumulated enough votes to show up at the top.
I could have linked to my blog post about it, but instead I linked to a Hacker News comment precisely because I anticipated complaints about "spamming" if I linked to my blog.
> I haven’t been involved with Django since leaving the Journal-World back in September, but now that the framework is open-sourced I look forward to contributing to its further development—both in terms of documentation and actual code.
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”.
Once again, continues to gaslight after spamming a post with another top-posted comment after having to “justify” it. In this case, You already admitted to it.
There is just no end or need to rapidly post on every opportunity that involves “AI” or whatever that is related to it.
Or an easier question: how am I gaslighting here? You should be able to spell that out.
(You do understand that the top linked site here was built by me, but has no authorship information on it at all, right? That's why I posted a comment explaining what it is.)
.. I know its tempting to try to reply to all these people but I'd just ignore them. A lot of them feel stressed by AI and it has nothing to do with you personally.
Spam = excessive promotion of your work. It’s not one comment, but the entire context of all your comments.
Gaslighting because it’s so OBVIOUS that this is what people are referring to by “spam” that you almost have to be purposely pretending to not understand. Such a prolific writer simply has to be aware of the fine line where promoting your work becomes excessive.
Someone else posted his site to HN, not Simon. He responds with additional context and also responds to links to other HN comments he’s made rather than just linking back to his own site. The only person gaslighting here is you.
I just tune out every post that says “I wrote about this already” and then links to it. Simon is great and kudos for his self promotion but it’s interesting to see as it’s often called out for anyone else.
The guy is good but he certainly stretches the limit. I just auto ignore his stuff but I know others enjoy!
If I use Codex in one session on desktop can I then resume it for cloud and mobile sessions as Work? Or do I have to make separate sessions each time? Or rather, can Codex in the cloud do the same things, if such a thing exists?
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.
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.
This can be replaced, you just have to do the work of building a design library yourself and the guidance components. Then building skills around their use.
I think these guideline are built into the llms. After all with llms, any decision you don't take will be taken for you. For a so called slop site (Simon's words, not mine :P) I don't think they specified a style so the llm just decided the default it knows. One day I will run experiments (when I can afford it) trying to identify the "taste" of different llms.
It tells ChatGPT Work how to launch a Playwright instance via its Node.js REPL, and tells it to run:
To get further instructions.That method returns this text with full details about how to use the browser: https://codex-tool-reference.simonw.chatgpt.site/skills/cont...
I'd love to know why it's defined like that, as opposed to including all of the instructions directly in the skill Markdown file.
Simply loading the browser Skill alone, doesn't always mean a browser is actually necessary (or supported). The user might've want them to control their main desktop browser; or the user might be pointing them toward a read-only HTML file that doesn't need rendering; or the sandbox might prevent network access; etc...
Codex is especially 'keen' to use Skills (especially by comparison to Claude), I often see it load Skills which it doesn't go on to use, because the main Skill content says "when not to use this". So I'm sure this is a product design decision to help with those kinds of circumstances.
Skill file could indicate general instructions for all browsers. This provides guidance for the browser that's about to actually be used.
I realize that for some people there is too much LLM-related content and (therefore?) too much by certain authors, but that has always been the case for certain topics and certain authors in HN's history. This is a side effect of the frontpage being the same for everyone, and therefore the scarcest resource.
https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
Someone else submitted my vibe-coded slop site to the front page without any context, and it accumulated enough votes to show up at the top.
I could have linked to my blog post about it, but instead I linked to a Hacker News comment precisely because I anticipated complaints about "spamming" if I linked to my blog.
> I haven’t been involved with Django since leaving the Journal-World back in September, but now that the framework is open-sourced I look forward to contributing to its further development—both in terms of documentation and actual code.
> Simon, stop using this forum to spam on every opportunity.
(I think you may be confusing "spam" with "prolific". I write a lot.)
There is just no end or need to rapidly post on every opportunity that involves “AI” or whatever that is related to it.
Or an easier question: how am I gaslighting here? You should be able to spell that out.
(You do understand that the top linked site here was built by me, but has no authorship information on it at all, right? That's why I posted a comment explaining what it is.)
"No, it's the children who are wrong".
Gaslighting because it’s so OBVIOUS that this is what people are referring to by “spam” that you almost have to be purposely pretending to not understand. Such a prolific writer simply has to be aware of the fine line where promoting your work becomes excessive.
Not taking sides here.
The guy is good but he certainly stretches the limit. I just auto ignore his stuff but I know others enjoy!
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.
(1) https://www.newyorker.com/magazine/2026/04/13/sam-altman-may... (2) https://thenextweb.com/news/openai-preparedness-team-disband... (3) https://thezvi.wordpress.com/2026/08/29/metr-and-redwood-off...
Are they following some sort of common guideline?
Scroll down to the "Establish the visual direction" section.