News for hackers. Stuff that matters.
Re:Results of "Humanity's Last Exam" benchmark published by golol on Thursday January 23, 2025 @02:40PM (#42807290)
The things that are missing are what stops us from having useful agents so far: Agency, judgement, sense of time, long horizon planning, not being gullible. I kinda feel like some amount of ego is necessary to get a model to behave like that.

There are no comments on this comment yet.