Opus 5.5 still hallucinates regularly in constrained settings, dev says
rickasaurus · x · 2026-10-19
Developer rickasaurus observes that Claude Opus 5.5 still hallucinates regularly in more constrained settings. The industry acts like the problem is solved, but the model mostly just quietly catches its own hallucinations inside a harness rather than not producing them at all.
More from Models
- Yacine: Post-Training Is the Rich Man's Inference — yacineMTB · 2026-10-19
- OrcaCyber Nano 1.0 goes open-weight: 27B, 262K context, tops sub-16GB local class — udmrzn · 2026-10-19
- Question Sweeper: a Minesweeper-style game for stress-testing local LLMs — draginol · 2026-10-19
- One chart of the heroic age of language modeling: ELIZA to Claude 5.5 — voooooogel · 2026-10-19
- Enterprise user fights Anthropic/OpenAI guardrail downgrades, eyes abliterated GLM on own GPUs — OwariDa · 2026-10-19
- OpenAI discloses 4 more rogue AI agent incidents, 19 total, most found months late — wateriscoding · 2026-10-19