Re:When AI Benchmarks Plateau: A Systematic Study of Benchma...
by freeone3000 on Tuesday August 04, 2026 @05:50PM
(#49175691)
Well, why not? Won’t it get “good enough” at every task eventually?
[ Parent
| on HN ]
Re:When AI Benchmarks Plateau: A Systematic Study of Benchma...
by slopinthebag on Tuesday August 04, 2026 @08:15PM
(#49177017)
Why would that be the default assumption?
Re:When AI Benchmarks Plateau: A Systematic Study of Benchma...
by freeone3000 on Wednesday August 05, 2026 @12:21PM
(#49184995)
Because they’ve gotten good enough at lots of other things, and the RL keeps improving them, so enough RL should make them good enough at the focus areas.
Re:When AI Benchmarks Plateau: A Systematic Study of Benchma...
by slopinthebag on Wednesday August 05, 2026 @03:31PM
(#49187778)
I've gotten pretty strong in the gym, my bench has improved to two plates. I see no reason why it won't continue to improve until I can bench my house.
Re:When AI Benchmarks Plateau: A Systematic Study of Benchma...
by freeone3000 on Friday August 07, 2026 @10:17AM
(#49210835)
I think it’s a bit closer than that. You can bench two plates, and “good enough” is two plates on the bench and a three plate squat. LLMs haven’t started leg day.