Ethan Mollick: Opus 4.7-5 lost the 'Claude feel', Opus 5.5 brings it back
emollick · x · 2026-09-27
Ethan Mollick argues model personality matters in ways benchmarks can't capture: the Opus line went through a rough patch from 4.7 to 5 where it no longer felt "Claude-y" — more like a watered-down Fable, possibly due to teacher-model distillation — while Opus 5.5 feels like working with ol' Claude again.
More from Models
- Claude 3 Opus Finds Zero-Days in Source Code, Sparking AI Risk Debate — JasonDClinton · 2026-09-27
- Tokens Keep Getting Cheaper Per Usefulness — Your View of What's Possible Is Stale — avt_im · 2026-09-27
- Jev takes 27% of OpenRouter classification requests, 2x DeepSeek V4 Flash — gaganghotra_ · 2026-09-27
- Claude Opus 5.5 makes its own 20-page sketchbook: handwriting, doodles, and piano music — CurieuxExplorer · 2026-09-27
- OpenAI strips 5x/10x/20x usage multipliers from plan upgrade UI, leaving vague wording — ssh4net · 2026-09-27
- Puppy Kill Bench: most models refuse, GPT6-Luna just executes the kill tool — MetroidsSuffering · 2026-09-27