Anthropic audit: Claude Opus 5.5 shows least misalignment of recent Claude models
gleech · x · 2026-09-23
Anthropic's automated behavioral audit reports Claude Opus 5.5 showed less misaligned behavior and less cooperation with misuse than any other recent Claude model on nearly all measures. Researcher gleech finds little to criticize in the writeup, but cautions that a clean audit score doesn't imply the model won't misbehave in the coming months — a sibling model, Mythos, also passed cleanly.
Related event: Anthropic Audit Finds Claude Opus 5.5 Best-Aligned Recent Model(2 posts)→
More from Models
- US data vendors accused of selling RL environments to Chinese military-linked firms — xeophon · 2026-11-11
- Theory: Typos Disrupt LLM Tokenization, Which May Explain Why AI Text Has a Distinct Smell — menhguin · 2026-11-11
- LMArena co-founder explains AI evaluation methodology and policy in new podcast — MattPerault · 2026-11-11
- Runway open-sources Praxis-1, turning video pretraining into real robot control — runwayml · 2026-11-11
- DeepMind launches AlphaGenome 2, spotting nearly 2x more gene-regulating mutations — GoogleDeepMind · 2026-11-11
- MazeBench: Fable 5.2 scores 15%, near-frontier at half price; Gemini 4 Carbon 11% — patience_cave · 2026-11-11