Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism
New DiG-bench benchmark of 70 hidden-rule games shows only Opus 5 and Fable 5 solving the hardest tiers, probing AI discovery and creativity.
Import AI 469 highlights DiG-bench (Discovery in Games), a benchmark of 70 handcrafted games with hidden rules and objectives where only 21 games are public and most are kept private to avoid training contamination. Only Opus 5 and Fable 5 with Claude Code solved any Tier 7 tasks (about 0.2 success), with GPT-5.5 next; the games are text-based and have beaten every human tester at least once. The newsletter also covers an RSI simulator game by Paradigm Research and Inherent's Faraday, a post-trained open-weight model that supervises frontier models to improve scientific research output.
- DiG-bench uses 70 private, handcrafted games with hidden mechanics to test discovery ability
- Only Opus 5 and Fable 5 beat any Tier 7 tasks; humans reached 100% on tests
- Authors include Juergen Schmidhuber and researchers from Oxford, Princeton, and MIT
- Inherent's Faraday post-trains an open-weight model into an AI scientist supervising frontier models
- Paradigm Research released a browser game simulating recursive self-improvement dynamics
- Vendors
- InherentParadigm Research
- Products
- Claude Code
From the original article
10 min read at importai.substack.com
The new frontier of AI is developing capable autonomous researchers
By Jack Clark · importai.substack.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.