Jeff AtwoodI have no idea what the source of this image is, but yeah, I Laughed Out Loud.
Bill the Lizard@codinghorror We should've just been nicer, I guess.
@lizardbill the funny thing is, the LLMs actually solve a HUGE problem for SO -- the endless repetition of the same questions over and over using slightly different words. I had NO idea how we would fix that, but now .. I kinda do?
aburka 🫣@codinghorror @lizardbill lol. Ask your mods if LLMs have been a net benefit.
Worik@aburka @codinghorror @lizardbill
> Ask your mods if LLMs have been a net benefit.
Ask me. Yes.
It is a tool that must be wielded by a hand. I do not think LLMs are going to be able to make reliable agents.
Unreliable agents are useful for some things, but reliable agents would be much more useful. Order of magnitude.
I want L5 automatic driving, I will not get it with current technology.
....liars
@worik @aburka @lizardbill I don't really like LLMs for code at all because such extreme precision is required in the language. That's not true of many other domains.
@codinghorror @aburka @lizardbill
> extreme precision
That is what makes it possible, and so useful, for code.
It has to be widely used code, which is why I have found it useful for learning Shell, and hopeless for designing Pure Data patches. (https://puredata.info/)
@worik @aburka @lizardbill I disagree, I think it is one of the riskiest use cases, but it's possible. It would need to vetted HEAVILY by a human.