More guesses: Anthropic may distrust LLMs reasoning over their own training
1a3orn · x · 2026-11-10
More guesses from 1a3orn on why Anthropic avoids inoculation prompting: (2) Anthropic may be spooked in general by LLMs reasoning over their own training process, and inoculation prompting makes that more likely; (3) they may simply prefer to trust their RL-env debuggers over the LLM.
More from AGI Musings
- MIRI launches "Do Not Accept" campaign against AI firms' superintelligence race — wfithian · 2026-11-10
- Claude builds a 500,000-tile mosaic engine, sparking the 'tasteslop' debate — teortaxesTex · 2026-11-10
- Economists note LLM analysis lacks the incentive to exaggerate effects like public debate does — robseamans · 2026-11-10
- Wharton scholar asks: what are institutions for in an age of AGI? — danielrock · 2026-11-10
- Schmidhuber: Physical AI progress is overestimated, human-level physical intelligence not within 2 years — SakanaAILabs · 2026-11-10
- Panel: if consciousness is computational, what follows for each discipline? — burny_tech · 2026-11-10