LessWrong

LessWrong (30+ Karma)

Goditi coinvolgenti letture audio di post perspicaci della comunità LessWrong, perfette per coloro che cercano contenuti stimolanti sulla razionalità e sul processo decisionale.

Listen on Apple Podcasts

[Linkpost] “Reasoning-Finetuning Repurposes Latent Representations in Base Models” by Jake Ward, lccqqqqq, Neel Nanda

6 mins • Jul 25, 2025

Episodi recenti

Jul 25, 2025

[Linkpost] “Reasoning-Finetuning Repurposes Latent Representations in Base Models” by Jake Ward, lccqqqqq, Neel Nanda

6 mins

Jul 24, 2025

“Building and evaluating alignment auditing agents” by Sam Marks, Sam Bowman, Euan Ong, Johannes Treutlein, evhub

11 mins

Jul 24, 2025

“The Whole Check” by JustisMills

7 mins

Jul 24, 2025

“‘Behaviorist’ RL reward functions lead to scheming” by Steven Byrnes

21 mins

Jul 23, 2025

“Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning” by kh4dien, Helena Casademunt, Adam Karvonen, Sam Marks, Senthooran Rajamanoharan, Neel Nanda

12 mins

Lingua
Inglese
Paese
Regno Unito
Richiedi un aggiornamento
Gli aggiornamenti potrebbero richiedere alcuni minuti.