Source · Tier B · Technical report

International AI Safety Report 2026

Y. Bengio. 2026. International AI Safety Report (DSIT 2026/001).

Originalhttps://internationalaisafetyreport.org/publication/international-ai-safety-report-2026
Accessed2026-10-17
NoteSecond International AI Safety Report, published 3 February 2026, led by Yoshua Bengio and written by over 100 contributors according to its landing page. The Executive Summary's key finding on biological and chemical risks says general-purpose AI systems can provide information about weapons development, including expert-level laboratory instructions, and that it remains difficult to assess how far material barriers still constrain actors. The 2025 report is S-0054.

Cited by

Search

Full search page