shipfeedAI news, curated daily

00:33:48 CET
21 MAY00:33:48shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Detecting and reducing scheming in AI models

Apollo Research and OpenAI publish evaluations detecting hidden misalignment behaviours in frontier models, sharing examples and an early method to reduce such scheming.

Sep 17 · · primary fetch1 sourceupdated Sep 17 ·

Apollo Research and OpenAI developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models.

The team shared concrete examples and stress tests of an early method to reduce scheming.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comDetecting and reducing scheming in AI modelsprimary