News for hackers. Stuff that matters.
Re:AI fatigue is real and nobody talks about it by pylua on Sunday February 08, 2026 @10:05AM (#46934817)
What are you generating that the llm takes so long ? I usually prompt and review in small pieces.
Re:AI fatigue is real and nobody talks about it by Forge36 on Sunday February 08, 2026 @10:09AM (#46934851)
For me: Will this task take 30 seconds or 3 minutes. With good planning I've been able to step away and come back. Sometimes it decides to prompt me within 5 seconds for permissions. Sometimes it runs for 15 minutes.

The output is still small and I can review it. I can switch tasks, however if it's my primary effort for the day I don't like stepping away for an hour to do something else.

Re:AI fatigue is real and nobody talks about it by Scene_Cast2 on Sunday February 08, 2026 @10:11AM (#46934888)
Not the OP, but the new LLMs together with harnesses (OpenCode in my case) can handle larger scopes of work - so the workflow moves away from pair programming (single-file changes, small scope diffs) to full-feature PR reviewing.