LessWrong11 min read
When AI Advice Shapes the Evidence It Later Interprets
SummaryAn AI assistant might recommend how to approach a friend, then be asked to interpret that friend's reaction. The reaction may look like an independent confirmation of the assistant's earlier assumption about the situation, even though the recommended approach may have played a role in…
By LessWrong

Read the full story
Originally published by LessWrong on Oct 19, 2026.
Comments
Sign in to join the discussion.