Skim Logo
80,000 Hours13 hours ago
Godfather of AI: How To Make Safe Superintelligent AI – Yoshua Bengio
2:35:26
8H

Godfather of AI: How To Make Safe Superintelligent AI – Yoshua Bengio

Bengio: Guaranteed Truths and Program Understanding — 80,000 Hours

From Godfather of AI: How To Make Safe Superintelligent AI – Yoshua Bengio. Category: Tech. Format: Interview. This is a single keypoint from the analysis.

Yoshua Bengio reassures that a small percentage of error in verified truths is acceptable. He points to guaranteed truths like mathematical theorems with formal proofs and, crucially, computer programs, as reliable data sources. Understanding programs allows AI to predict outputs, providing hard, incontestable facts.

Impact: High. This clarifies the practical sources of 'verified truth' for the Scientist AI, emphasizing computational and mathematical domains as robust foundations, which can then inform reasoning about more ambiguous areas.

In the source video, this keypoint occurs from 01:31:05 to 01:32:07.

Sources in support: Rob Wiblin (Host)

For the full credibility analysis, key takeaways, and other keypoints from this video, see the full analysis on skim.

This keypoint analysis was generated by skim (skim.plus), an AI-powered content analysis platform by Credible AI.