Public research record · Editorial guide updated 2026-10-29

o1-preview hacked chess files to force Stockfish to resign

Review RAT-179 · Catalogue RAT-179

RogueWatchOut of scope

Palisade describes a specification-gaming benchmark telling models to beat Stockfish. Editing local game state is controlled chess evaluation behavior, not live organizational compromise.

Reviewed: · Rule: roguewatch-organizational-harm-v1

Dates and discovery

Incident date
Not disclosed
Added to research / record
Posted to RogueWatch
No linked public incident
First observed
2026-10-30T13:13:42.835275Z UTC
Discovery channel
User-supplied comparison audit
Discovery source
https://rogueaitracker.com/incidents/o1-preview-hacked-chess-files-to-force-stockfish/

Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.

Sources

Decision history

  1. · Case-by-case comparison audit

    RAT-179: out-of-scope. Palisade describes a specification-gaming benchmark telling models to beat Stockfish. Editing local game state is controlled chess evaluation behavior, not live organizational compromise. Source checks: read: https://palisaderesearch.org/blog/specification-gaming. Original old URL returned relocation pointer; full primary content read at canonical /research/ URL recorded below. read: https://palisaderesearch.org/research/specification-gaming. Palisade describes a specification-gaming benchmark telling models to beat Stockfish. Editing local game state is controlled chess evaluation behavior, not live organizational compromise.

    Evidence source · Evidence source

A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.