Hacker Timesnew | past | comments | ask | show | jobs | submit | ElFitz's commentslogin

My favourite so far was Claude "fixing" deployment checks with `continue-on-error: true`

Our sales and marketing have started making their own tools for themselves. This week. They actually launched a terminal.

They hit a wall with deployment, for now, but it’s amusing to watch.

And since I wouldn’t trust their stuff (or Claude’s) with a 10-mile long stick I strongly suggested we put it on Cloudflare behind eight layers of Access / Zero Trust. Easy deployment, and "solves" (if we can call it that) many of the security issues (or not; maybe I’m wrong).


> What value is left to provide for users?

Everything and anything people actually want or need, whether it’s every day or just for five minutes, that nobody else could be bothered to make.

Today most won’t know what to do with it, just like they didn’t know what to do with a web browser.

But that won’t last.


Iterative multi-agent and multi-model processes are fun.

Why would the synthesis round get expensive than the regular rounds?

> and quickly realized throwing 5 mediocre models at a problem just makes them argue in circle.

What was your selection strategy? My current issue is more that the more models I add, the less likely any specific one is to win two rounds in a row. Which would make perfect sense no matter the model quality, no? Unless there’s a huge gap.

> For brainstorm mode maybe weight models by past accuracy instead of pure voting?

By adding outputs history and a way to track the actual outcomes?


More than that. Building a throwaway-transient-single-use web app for a single annoying use kind of makes sense now, sometimes.

I had to create a bunch of GitHub and Linear apps. Without me even asking Codex whipped up a web page and a local server to set them up, collecting the OAuth credentials, and forward them to the actual app.

Took two minutes, I used it to set up the apps in three clicks each, and then just deleted the thing.

Code as transient disposable artifacts.


I posted it recently, but now this works differently https://xkcd.com/1205/

You can get a throw away app in 5 mins, before I wouldn't even bother.


This. So much. Nobody cares whether it’s AI or goblins under the hood. Just like nobody cares about how smartphones or the internet work. The only thing that matters to the majority of user is what it does for (or to) them.

Apple’s marketing was (is?) textbook this.

Also, I’d bet most people building with LLMs don’t care, or even know about, PyPI.


People just don’t learn do they?

It’s truly amazing. This is why I’m not surprised people are ‘blown away’ by llm’s. They were never truly intrinsically intelligent - they were expert regurgitators of knowledge on demand.

Steve already suffered from immense scar tissue of starting with the technology. And yet.. this wisdom blows over peoples minds. More fool them.


> Steve already suffered from immense scar tissue of starting with the technology.

Funny. I just stumbled upon that specific OpenDoc video today.

https://youtube.com/watch?v=oeqPrUmVz-o


That’s exactly what I was referencing :)

> how OpenAI is not-so-subtly adopting a social-network-esque model, in how it's fine-tuned its chat system to always suggest another question that the user might want to ask.

There’s that, but it could also be adaptation to the fact users… just don’t know what to do with it.

Just like the prompt suggestions they added for new conversations a little time after releasing the first app. Those seem to be mostly gone now, at least on mobile.


Now with NFTs and pixel art, memorialising each and every one of your deleted emails in a unique and non-fungible way.

Now I actually want to make it, and build a "card trading game" on top of it.


It's one of the things that surprised me when I first started using the compound engineering plugin.

I've been considering adding a review gate with a reviewing model solely tasked with identifying gaps between the plan and the implementation.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: