thierrydamiba

Awesome story, thanks for sharing!

Or you’re getting steered into la la land because of your prompt

Have they ever talked about what goes into the classifier? I wonder how much your past chats impact it.

For example if it knows you do X at Y company is it more or less strict?

Is the harness more valuable than the weights?

Awesome article! Love the way you went from physically to digital.

There’s also the uncomfortable reality that a lot of people spent a lot of time learning how to do things that anyone can prompt now…

We tend to ignore that reality but it hangs above all these discussions like a dirty cloud

Did your son behave in a way for that to be installed or did you do it by default?

People will pay out of the nose for software if they find it useful enough.

I’m not sure this is so true. Anthropic and OpenAI are both heavily hiring for humans in enterprise roles. Safe to say they are using AI as much as possible and they need humans too.

Can you be more specific?

The scary thing for me is most of the vulnerabilities have been revealed due to silly mistakes.

If someone really knew what they were doing and had bad intentions, I fear we would never find out.

This story deserves a movie, or at least a long video essay!

Haven’t laughed this hard in a long time.

This is as close as you get to a win win in life.

Shoutout to you-I will match it if they need other resources. (I don’t work at OAI, just think this is cool)

Is your stack really that rough?

Recommend everyone take this test: https://www.nytimes.com/interactive/2026/03/09/business/ai-w...

You might be surprised…or you might not. I’ve found it’s a good barometer for whether you actually don’t like AI writing or you just don’t like bad AI writing.

They basically bought OpenClaw right?

Something really magical about “Distributed Version Control System” sharing an acronym with “Disney Vacation Club Services”.

What’s different about the market in China that enables this?

Isn’t this a great use of llms?

Clone the repo in a sandbox and have the llm identify if the issues are real and the appropriate response based on severity level.

Wouldn’t be perfect but would have caught something like this.

Same reason people get scared to fly but drive everyday. Humans are simultaneously wildly irrational and terrible at calculating risk.

This thread is simultaneously horrifying and hilarious at the same time.

Hilarious because onesociety2022 seems so earnest. Someone who is shocked at the idea that job search isn’t a pure meritocracy.

Horrifying because kuang_eleven points out just how easy it is to pass a qualified candidate if you want to.

The truth is somewhere in the middle…

I don’t understand this comment?

I’m guessing you’re suggesting it’s ok to lose time if you’re away from your computer enjoying life, and I agree. I also don’t see the issue in finding ways to be save time with work.

If you mean something different, please elaborate.

I actually look at this another way. I think we’re going to see a lot more open source. Before you had to get your pr merged into main. Now people will just ask ai to build the tool they need and then open source it.

Maintainers won’t have to deal with an endless stream of PRs. Now people will just clone your library the second it has traction and make it perfect for their specific use case.

Cherry pick the best features and build something perfect for them. They’ll be able to do things your product can’t, and individual users will probably find a better fit in these spinoffs than in the original app.

On the other hand, you lose a lot of time if you step away from a session and it gets stuck asking for permission to do something simple.

Can you talk more about this? What’s wrong with cloudflare pages plus Nextjs? Why do you need Astro?

Thanks

No I don’t think it’s a bad thing!

I’m just predicting what will happen. I think it’s a really good thing.

I’ve been thinking about this idea a lot. I have a phrase that I’ve taken to using. Leverage Engineering.

I think AI is going to create a whole new class of people that take a tiny output and turn it into an outsized output.

When this works, it is really nice. Think Cursor, Lovable, or OpenClaw.

When it doesn’t work though, things get ugly too. The same power that allows a small team to build a billion dollar company also allows rouge agents to industrialize their efforts as well.

Combine this with the rise of headless browsers and you have a dangerous cocktail.

I wouldn’t be surprised if we see regulation or licensing around frontier AI APIs in the near future.

I'm building a benchmark for coding agent memory following your philosophy. There are so many memory tools out there but I have not been able to find a reliable benchmark for coding agent memory. So I'm just building it myself.

A lot of this stuff is really new, and we will need to find ways to standardize, but it will take time and consensus.

It took 4 years after the release of the automobile to coin the term milage to refer to miles driven per unit of gasoline. We will in due time create the same metrics for AI.

Try ghostty, wterm, or kitty as the terminal you run Claude code from. Much better experience.