Interpretability researcher pleads with Anthropic to stop banning him; screenshot shows claude-opus-5-5
Sauers_ · x · 2026-11-11
Researcher Sauers publicly asked Anthropic to "stop banning me; I'm doing interpretability research," with a screenshot showing Claude Code hitting a 403: model "claude-opus-5-5" is suspended for the organization until 2026-11-11. The error also accidentally reveals the unreleased model name — safety research tripping the very guardrails it studies.
More from Fun
- Grok caught using British spelling 'colour', joked as 'trained on European data' — verrsane · 2026-11-11
- Seedream 5 nails darkfield microscopy: AI diatoms with glass shells and chloroplasts — CurieuxExplorer · 2026-11-11
- AI-made Dreamcast game got 115 upvotes before removal: 'AI haters are a minority' — AIandDesign · 2026-11-11
- Cube-Solving Robot Demo Is Its Best Case: ~90 Moves per Solve on Average — haydendevs · 2026-11-11
- Gemini 4 Carbon nails a striking single drop of blood simulation — AI_Andrew · 2026-11-11
- Perplexity CEO quips: 'The perplexity of the universe is destined to increase' — AravSrinivas · 2026-11-11