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

Understanding ChatGPT Work

simonwillison.net

Post reply on HN
Print view View original

201–210 of 216 posts

Re: Understanding ChatGPT Work

#201

Post by russellbeattie »

xatxat wrote: post #33

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 :)

Nice! I regularly do this with Claude to create little web apps on my phone, so that's great idea to create little Android apps instead!

Amusingly, I started walking recently at a local track. One day while I was walking, I thought, "I should create a little web app for a counter to keep track of my laps." So I asked Claude Code and it whipped up a nice little mobile app with a big "+1" button, a reset, the whole deal, all within less than a lap and a half. Great! A lap later I think, "I should have it keep track of the time it takes me to walk each lap."

As I'm typing out the description, I realize, "You dumbass, you're describing the built-in chronograph feature of the Clock app!" So I just switched to that.

Re: Understanding ChatGPT Work

#202

Post by tuesdaynight »

simonw wrote: post #93
FinnKuhn wrote: post #92

Earlier quoted context omitted.

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.

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.

Didn't OpenAI hire him? I thought it was not a secret that OpenClaw was the biggest influence.

Re: Understanding ChatGPT Work

#203

Post by Wolfenstein98k »

matsemann wrote: post #101
safety1st wrote: post #64

Earlier quoted context omitted.

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…

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.

Don't confuse "Ben can answer these emails in 20 minutes" with "anyone could answer these emails in 20 minutes"

Imagine you could get Elon to answer your emails. Is that perfectly interchangeable with any other human?

Re: Understanding ChatGPT Work

#204

Post by shostack »

mrngld wrote: post #120
ozgung wrote: post #98

Earlier quoted context omitted.

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 gran…

You don't have to go to the HuggingFace incident! Go back in time to the New York Times legal brawl where NYT lawyers started being able to scoop up all their logs not covered by a ZDR. That's what keeps me from giving OpenAI access to anything too personal. My employer offers to let us use our corporate seats for personal stuff so we can be covered by our corporate ZDR, but AFAIK that enables HR to see all my chats…

You can have OpenRouter filter for ZDR providers. There are nuances like contractual ZDR vs technical ZDR but definitely worth investigating

Re: Understanding ChatGPT Work

#205

Post by shostack »

safety1st wrote: post #64
tristanj wrote: post #4

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 sav…

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…

I consider myself fairly AI native. I was absolutely blown away by how frictionless it felt the other day interfacing with codex using the experimental headless app server on my VPS and using voice mode on my phone connected to it while I had my browser open having a conversation about making edits to my website.

The site uses Astro to hot load edits and so the exceptional Live voice model would use some filler words in response to me asking for an edit and before I knew it, the page had refreshed with the fix.

When people talk about things like OpenClaw and Hermes being a new operating system paradigm this is the sort of UX that comes to mind.

And simply conversing with it with my phone in my pocket and air pods on its the closest I've felt to a live conversation with AI ever.

Kudos to the voice mode and Live voice model teams.

Re: Understanding ChatGPT Work

#206

Post by matsemann »

Wolfenstein98k wrote: post #203
matsemann wrote: post #101

Earlier quoted context omitted.

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.

Don't confuse "Ben can answer these emails in 20 minutes" with "anyone could answer these emails in 20 minutes" Imagine you could get Elon to answer your emails. Is that perfectly interchangeable with any other human?

It's kinda my point, though, that it's busy "manager" work if it really can be answered by an LLM. So yeah, getting answer from someone like Elon is exactly as useful as just asking the LLM myself.

Re: Understanding ChatGPT Work

#207

Post by Gud »

ExtremisAndy wrote: post #108
ozgung wrote: post #98

Earlier quoted context omitted.

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 gran…

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 gr…

Me too, it is a crystal clear boundary between me and the LLM. They might have access to my most precious code, but at least they don't have access to my browsing history.

Re: Understanding ChatGPT Work

#208

Post by KronisLV »

embedding-shape wrote: post #169
ceejayoz wrote: post #153

Earlier quoted context omitted.

An agent with full access to your codebase is able to email out without supervision in response to an untrusted messsage?

Surely passing untrusted input to a agent with execution capabilities and also possibility to reply to the same author, couldn't possibly be used for anything negative? Parent is probably using a firewall so it's A-OK :thumbs_up:

> Surely passing untrusted input to a agent with execution capabilities

Oh hey, I know this one! It’s humans and a phishing test, they’ll click on all the links and enter information without checking the domain properly!

Personally, I’d like systems that aren’t open to attack and can be depended upon. But it seems like nowadays NOTHING can be trusted - not OSes (recent Qubes OS exploit, not even mentioning others), not any software written in languages without memory safety, not even the ones with (Log4j comes to mind), not the packages in many package managers, not other humans and sure as hell not the token prediction machines. What a world.

We all probably live with a 0.XX% chance of getting pwned any given day.

Re: Understanding ChatGPT Work

#209

Post by embedding-shape »

KronisLV wrote: post #208
embedding-shape wrote: post #169

Earlier quoted context omitted.

Surely passing untrusted input to a agent with execution capabilities and also possibility to reply to the same author, couldn't possibly be used for anything negative? Parent is probably using a firewall so it's A-OK :thumbs_up:

> Surely passing untrusted input to a agent with execution capabilities Oh hey, I know this one! It’s humans and a phishing test, they’ll click on all the links and enter information without checking the domain properly! Personally, I’d like systems that aren’t open to attack and can be depended upon. But it seems like nowadays NOTHING can be trusted - not OSes (recent Qubes OS exploit, not even mentioning others), n…

> But it seems like nowadays NOTHING can be trusted - not OSes (recent Qubes OS exploit, not even mentioning others),

Clearly you feel alarmed, but it's important to base these "alarm" feelings on actual evidence and real concrete proof of something being bad. You clearly don't have a proper understanding of the exploit, so please take a moment to re-read what actually happened and how it would be exploited in practice, particularly the "the scope of this attack is smaller than it sounds" comment chain: https://news.ycombinator.com/item?id=49496918

Overall, I agree with you though, and it's a healthy perspective to be safer rather than sorrier, so living with the assumption that getting pwned any day is a non-zero chance/risk is probably the best approach and what I personally do too.

Re: Understanding ChatGPT Work

#210

Post by jimmydoe »

this is helpful piece.

Claude app struggles in its UX navigation, they moved code/cowork/design a couple of times in app ui, but never confusing for users to understand what each of these three non-chat pieces does.

ChatGPT sub is so confusing, OpenAI must either hate users or don't have a real product manager.

Post reply on HN