Hacker News new | ask | show | jobs
by red75prime 53 days ago
Desarcasmed version: "I think that problems with Zork make those models virtually useless in programming tasks." Correct?
1 comments
cptskippy 53 days ago
He said complicated code bases. LLMs are great at producing small snippets of code to address very targeted problems.
link
red75prime 53 days ago
Great on small snippets of code, passable on larger pieces of code, great at finding vulnerabilities in large pieces of code, terrible in Zork. All-in-all, a jagged frontier that defies a simple sarcastic characterization.
link
girvo 53 days ago
Very kiki, not very bouba, as Aphyr rightfully stated.
link