Alexander Panfilov(@kotekjedi_ml):2) Illegible reasoning: We confirm prior reports by @ApolloResearch: OpenAI models sometimes reason in alien-like language, referring to themselves as “we” or “it,” or spiraling into cursed loops of “vantages,” “marinades,” and “watchers.” CoT-monitoring people are doing God’s work, as in many traces, even with the prompt, it’s just impossible to tell what the model is up to. We show more examples at

Alexander Panfilov

@kotekjedi_ml

MATS 9.0 | PhD @ELLISInst_Tue & @MPI_IS doing AI Safety & Adversarial ML

参加 October 2013

403 フォロー中 9.5K ファン

Alexander Panfilov@kotekjedi_ml

2026.08.11 12:00

2) Illegible reasoning: We confirm prior reports by @ApolloResearch: OpenAI models sometimes reason in alien-like language, referring to themselves as “we” or “it,” or spiraling into cursed loops of “vantages,” “marinades,” and “watchers.” CoT-monitoring people are doing God’s work, as in many traces, even with the prompt, it’s just impossible to tell what the model is up to. We show more examples at