News for hackers. Stuff that matters.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by latentsea on Tuesday November 17, 2026 @11:08AM (#50533426)
This is why for open-weights models at least harness aware post-training is becoming a thing. Also closed source harnesses that aren't fully editable are basically an anti-pattern. The labs should just hurry up and productionize self-evolving harnesses, and have the models internalize harness engineering, so they can optimise the harness for the given task. These are solvable problems.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by Alwayshasbeeb on Wednesday November 18, 2026 @05:14AM (#50544345)
This. I have coworkers who are really smug about claude code being "the best" option for AI assisted development and who refuse to try anything else. They also constantly submit pull requests littered with trash "trace of thinking" slop comments and when I point it out they say "yeah I usually try to make it not do that but this one got through". Meanwhile in pi this was trivial to fix and I'm often mining session history to refine the efficiency.