Tracking AI existential risk. Auto-aggregated headlines. Human-curated analysis.
AGGREGATING 47 SOURCES · UPDATED LIVE
Analysis

The Human Substitution Test as a Sanity Check for AI Evaluations

Zac Boring July 12, 2026 1 min read
Read original source →

TL;DR: We suggest a sanity check for proposed evaluation or AI oversight schemes: Imagine the AI was replaced by a competent, strategic human — someone who knows they might get evaluated and has their own agenda. Would the evaluation still work?When we apply this mental move broadly, to all AIs and evaluations at once, we get a rather discouraging picture: The questions we care about the most — such as "Is it safe to give this AI more power?" — correspond closely to questions where we already kn

By VojtaKovarik

Read the full article at LessWrong AI →