News for hackers. Stuff that matters.
Re:Claude Fable 5 vs. GPT-5.5: Better Planning, Similar Exec... by justiceforsaas on Saturday June 13, 2026 @12:03PM (#48518544)
Honestly the code gen part has been “good enough” for a while now, especially with models like Opus. The broader point this post is making is that newer SOTA models are improving at the "planning layer", and this is usually the the part a senior developer would usually handle (identifying edge cases, thinking ahead, thinking about tradeoffs, etc.)
Re:Claude Fable 5 vs. GPT-5.5: Better Planning, Similar Exec... by dpbrinkm on Saturday June 13, 2026 @12:38PM (#48518907)
Was it really that bad when you would use skills like the superpowers pack?