shipfeedAI news, curated daily

06:47:25 CET
25 AUG06:47:25shipfeed
pull to refreshlast sync
Just in — 30 new
§ safety · storyline

Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty

Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty

yesterday · · primary fetch1 sourceupdated yesterday ·

This storyline groups 1 article from 1 source. The originating feed didn’t ship an excerpt — open any link below to read the piece.

read full article on arxiv.org
§ sources1 publication · timeline below
  1. arxiv.orgMitigating Reasoning-Induced Misalignment via Safety-Direction Penaltyprimary