Hacker Newsnew | past | comments | ask | show | jobs | submit | topaz0's commentslogin

That was a delicious read. I love this kind of mathematical writing.

It's a huge mistake to jump from "all recent presidents have abused executive power in some way" (accurate and bad, and we shouldn't stand for it) to "they are all the same/their abuses are equally extreme/damaging" (incredibly ignorant and incorrect)

Sounds like you're just fine depending on an extremely imprecise abstraction (natural language) and an extremely opaque third party (anthropic).

I think you're missing the point of the commenter. A third party library is a new dependency. Since there's new vulnerabilities almost every week in the npm ecosystem, if you can do something without a third party, it's probably better.

With LLM driven code you can generate code once, and then if anything is shitty about it you can always manually update it yourself without the need of an LLM. It's a dependency of convenience, not an app-dependency.


From the description of the recommended tool it sounded to me like something that you use to deterministically generate code from a spec, which you could then modify if you like. That would be the same kind of dependency as the LLM workflow you describe, except that the abstraction is well-defined in a way that the LLM is not. Whether it's good or not is a different question.

That would be nice if it were the case but from what I can gather from this interesting dependency graph, there's a hard dependency on its renderer and schema.

https://jsonforms.io/img/architecture.svg

You can add your custom renderer but you still need their library for bindings and such.


I can also just do it myself though lmao its not like I dont look at what it is producing

The recommended tool cant even produce mobile friendly, like why would I ever use it?


I don't know or care about that specific tool, or really what you do at all, I was just reacting to how the principle you stated conflicts with the practice you described. How you reconcile those is up to you.

GP is talking about what they [the companies in question] accept/expect as work product. That has always differed from what they look for in a job candidate. Not surprising that AI psychosis amplifies the discrepancy.

Do you know how much it would have been at API prices?

Can't speak for their usage, but I calculated my token use with Copilot, my employer paid 22$ for >2000$ in tokens. Given estimates margins, Github is paying 98-99% of the costs for us. I imagine Claude max etc is similar. So it's not sustainable at all

No idea. Probably quite expensive. I usually run 4-5 concurrent CC sessions, so hard to pinpoint for just CHasm and Fe2O3

The idea that "agent harness" is the thing people actually want is laughable.


It seems it is the buzzword of the month.


Where in this case roi means attracting investments that will make the founders rich while making most of the investors lose money


I hope you inform our attorney general


Interesting that your thought process is failing in the same way that llms fail, which is though faulty analogies.


Curious, which API key are you using?


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

Search: