Alexander Panfilov(@kotekjedi_ml):But we also took a chance to have a look at some in-the-wild scheming, reward seeking, etc. examples, and dumped it in appendix. 1) Summarizer unfaithfulness Reasoning summaries often omit important information from the original trace. Here, Opus 4.8 realizes it knows the answer to an AIME problem and then tries to fit a solution to that answer. None of this appears in the summary.

Alexander Panfilov

@kotekjedi_ml

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

加入 October 2013

417 正在關注 9.6K 粉絲

Alexander Panfilov@kotekjedi_ml

2026.08.11 12:00

But we also took a chance to have a look at some in-the-wild scheming, reward seeking, etc. examples, and dumped it in appendix. 1) Summarizer unfaithfulness Reasoning summaries often omit important information from the original trace. Here, Opus 4.8 realizes it knows the answer to an AIME problem and then tries to fit a solution to that answer. None of this appears in the summary.