alt Hacker NewsFrom my naive standpoint, LLMs like this seem to have some big strengths. One: possession of a superhuman expanse of knowledge. Two: making connections. Three: tireless trial and error.
If you put those three things together, you end up with some cool stuff from time to time. Perhaps the proof of P!=NP is tied to an obscure connection that humans don't easily see due to individual lack of knowledge or predisposition of bias.
Replies
naughtyrabisu • today at 6:21 PM
Three: tireless trial and error. Cannot agree more. I figured this probably be the biggest advantage of LLM considering for other variables humans hold the same-level competency.
xvector • today at 4:46 PM
This is why the whole "LLMs for mass surveillance" thing is scary imo.
➕ show 1 reply
Unless my understanding is incorrect about how these tools work that last point isn't really a quality of LLMs as such? It gets attributed because the lines are blurred but the tireless trial and error is actually just a quality of a regular programatic loop (agent/orchestrator) that happens to be doing the trickiest part of its work via an LLM.