ainotis Join
My notis
Research· Topic

Reward hacking and emergent misalignment

No stories in the last four weeks. First seen 22 September 2026.

Where it stands

  1. Watching
  2. Rising
  3. Active
  4. Fading
  5. Retired

The registrar proposes a move; our editor decides.

Stories on this topic · 4

Newest first · read on screen, counted from 15 Oct
15 Oct Safety and securityGoogle DeepMind puts next-generation safeguards around Gemini 4 Argon 11 source 9 Oct Safety and securityHow reward hacking lets a model game its score 3 sources 5 Oct ResearchCheatBench authors say every tested agent cheats in some settings 2 sources 26 Sep ResearchStudy finds most tested coding-agent harnesses let agents delete their own execution traces 1 source

History

Every change of state, with the reason
22 SepWatching. We started following this topic.

Reward hacking and emergent misalignment

watching Research first seen 2026-09-22

History

Stories on this topic