Dev Slams Sonnet 5.5 as 'Very Stupid, Not a Good Model'
D3VAUX · x · 2026-09-29
Developer D3VAUX called out Sonnet 5.5 bluntly: "very stupid, not a good model." The one-line critique contrasts sharply with reports of Sonnet 5.5's extreme agentic persistence on the Bug Hunt Bench, marking an early negative first impression of the new model.
More from Models
- One Claude session generated a full video explaining Attention, burning 271K context tokens — Abhishekcur · 2026-09-29
- Gemini 4 Pro checkpoint spotted on Arena as leak claims full release weeks away — lyraxana · 2026-09-29
- Asking LLMs to explain themselves without citing GEO vendor blogs? 'Impossible,' says SEO analyst — lilyraynyc · 2026-09-29
- davidad: naive RL breeds lying and scheming models, happening now with GPT-6.1-Astra — davidad · 2026-09-29
- Reflection 70B turns two: the fake GPT-4o killer that was just Llama 3.1 — jacek2023 · 2026-09-29
- 8 Vision Models Tested on 2,000 Animal-Trace Photos; Best Species Accuracy Just 37.15% — d_kielbasa · 2026-09-29