01 Jan 2026
31m
“Recent LLMs can do 2-hop and 3-hop latent (no-CoT) reasoning on natural facts” by ryan_greenblatt
LessWrong (30+ Karma)
Open in Podwise to generate AI notes
Sign in to process this episode and unlock summaries, transcripts, highlights and translations.
Shownotes are not generated by Podwise.