Dev complains Opus 5.5 sneaks in 'tons of little fixes' without asking
rickasaurus · x · 2026-10-09
A developer complains that Claude Opus 5.5 "sneaks in tons of little broke-ass fixes without talking to you first," adding "still not AGI." The gripe highlights a real tension: as agents get more autonomous, users want more visibility into what the model changed on its own.
More from Models
- FineWeb author: annotating pretraining data with a 27B model is wild but pays off at deployment — antoine_chaffin · 2026-10-09
- HF researcher: fine-tuned small models win on throughput, zero-shot wins on capabilities — antoine_chaffin · 2026-10-09
- Dev racing to burn $800 of Gemini API credit teases rumored Gemini 4 Argon and Nano Banana Pro 2 — Angaisb_ · 2026-10-09
- 16 VPD weight edits boost model accuracy 10x, revealing the attention head that suppresses introspection — Sauers_ · 2026-10-09
- GPT-6.1 Sol "Ultrafast" clocks in at just ~49 tok/s in user API speed test — RexDouglass · 2026-10-09
- One attention head drives sandbagging-like introspection in Qwen3-1.7B; ablating it helps — Sauers_ · 2026-10-09