Live data from Hacker News

Why I'm still bearish on LLMs after Navier-Stokes

dank.systems

641–642 of 642 posts

Re: Why I'm still bearish on LLMs after Navier-Stokes

#641

Earlier quoted context omitted.

But what if I use the skills, and still can't model to follow it? Does the AI company say anywhere that they will refund the tokens if the model does not follow what is written in the Skills file? If there is no such guarantee, why should I spend time writing an elaborate skill file? There is no telling when the model chose to ignore stuff in it. I don't understand how people can work with something like that!

i think you miss the part about the loop. you're still building software for the past/current world. when you have chains of agents working seamlessly, where agents are managed by themselves (like spawning a new chain to do some scope of work), and it just sort of works on a infinite game loop, your system continually keeps improving as it works. at least, that is the goal with the systems i like to build. you have t…

Your use case totally makes sense.

The non-sense is the part where you think putting agents in a loop is going to yield better results indefinitely...

Re: Why I'm still bearish on LLMs after Navier-Stokes

#642

Earlier quoted context omitted.

lol. wish it was. fwiw i was pretty much bearish on AI for years because I did go deep into this shit since i got access to GPT 3. but since astra i have been quite bullish. 98% of people think AI means what gemini tells them when they do a google search. of that 2% who go beyond... maybe 20% of those are using AI to code. most SWE still think "using AI" to code means the copilot pane they open on the side in VSC. th…

> 98% of people think AI means what gemini tells them when they do a google search. > of that 2% who go beyond... maybe 20% of those are using AI to code. > so of that 20%, maybe 5% have... maybe 1-5% of that 5% actually went deeper How can you write any of this when you said you just started liking LLMs with Astra, a model that released two weeks ago. You're whipping out a bunch of made up stats trying to describe l…

I think he is someone who got burned by some bad software contractors in the past...
Post reply on HN