Import AI· Jack Clark·· 2026-08-17
Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism
Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism
AI summary
Import AI 469 introduces DiG-bench (Discovery in Games), with 70 games whose hidden rules and goals must be discovered through interaction. Opus 5 and Fable 5 with Claude Code performed best; only they completed some Tier 7 tasks, while humans achieved 100% completion.
Selection record
Threshold 76Media and individualsFirst 22Second 34
Not admittedSum of both 56 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：AI研究通讯，含AI基准与模型评测
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Import AI · importai.substack.com