Podcast·2024

Yoshua Bengio — AI Safety, Power Concentration, and Alignment Failures

by Yoshua Bengio

Listen→Editorial policy
Format
Podcast
Year
2024
Author
Yoshua Bengio
Frameworks extracted
1

About this source

Turing Award winner and Mila AI Institute founder Yoshua Bengio discusses AI misalignment mechanisms, the precautionary principle for catastrophic risk, power concentration as the #1 near-term AI risk, sycophancy as real misalignment, and his LawZero non-profit for safe-by-construction superintelligence.

Frameworks extracted

1 total
STRdays
Precautionary Principle for Catastrophic Risk
When the downside is irreversible, 1% probability is not a small number