Przejdź do treści
Global sound
AI Papers: A Deep Dive

AI Papers: A Deep Dive

Reading a Model's Internals to Tell 'Won't Say' From 'Doesn't Know'

· 13 min

Notatki do odcinka

Reading a Model's Internals to Tell 'Won't Say' From 'Doesn't Know'

Source: https://arxiv.org/abs/2609.21996
Paper was published on September 18, 2026

This episode was AI-generated on September 21, 2026. The script was written by an AI language model and the host voices were synthesized by Eleven Labs. The producer is not affiliated with Anthropic or Eleven Labs.

When a language model gives a wrong answer, there's no way from the outside to tell whether it never knew or is quietly withholding — and every 'we unlearned the dangerous capability' claim rests on that gap. One researcher…

Strona: paperdive.ai

Na żywo, ostatnia godzina: 13 152 utworów na 6 398 stacjach w 135 krajach

Odkrywaj świat przez radio

Więcej sposobów na odkrywanie (7)

Usłyszałeś coś fajnego? Zapisz to albo otwórz od razu w Spotify.

★ Artysta tygodnia Najszybciej rosnący w radiu w tym tygodniu
Twój utwór tutaj? Od € 9 tygodniowo →
Freedom LoveZone RadioSłuchaj dalej