News for hackers. Stuff that matters.
Re:Measuring AI Ability to Complete Long Tasks: Opus 4.5 has... by PessimalDecimal on Sunday December 21, 2025 @10:12AM (#46345382)
Forgetting LLMs and coding agents for a second, what OP describes is like watching a Youtube video on how to make a small repair around the house. You can watch that and "know" what needs to be done afterwards. But it is a very different thing to do it yourself.

Ultimately it comes to whether gaining the know how through experience is worth it or not.

Re:Measuring AI Ability to Complete Long Tasks: Opus 4.5 has... by viking123 on Sunday December 21, 2025 @12:03PM (#46346252)
It's like reading a math book.