David Krueger 🇨🇦
Machine-learning researcher whose work covers alignment, robustness, responsible AI, coordination, and risks from advanced systems.
Mila / Université de Montréal
- Evidence items
- 1
- Toward pressure
- +0.02
- Away pressure
- −0.00
- Net attributed pressure
- +0.02
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
MONITORED SOURCES
First-person and official sources
These sources guide discovery. A statement still needs a dated, attributable, source-backed evidence assessment before it can affect the index.
- institutional profileDavid Krueger
RELATED EVIDENCE
View all 1 items →
Assessments involving David Krueger
David Krueger warns scalable oversight can create circular safety arguments
David Krueger argued that scalable oversight can become circular when a supposedly safe AI assistant is used to validate a stronger system before the assistant's own safety has been established. He favored robustly aligning simpler, human-judgeable behavior and using both unaided and AI-assisted human review as safety filters.