laurenswhipple / ml / agi-to-asi

Open Research Questions (the actual agenda)

Section 7.1 of the paper. This is the part that turns the report from a survey into a call-to-action. Worth scanning if you ever want to choose a research direction here.

1. Bottlenecks & frictions for scaling

2. Quantitative forecasting

3. Benchmarking ASI

"Comparing against human performance will not produce useful signal to quantitatively distinguish superhuman AIs and AI innovations."

The proposed approaches: - Multi-agent benchmarks (zero-sum games — how chess engines are evaluated) - Setter-solver — AI generates the benchmark; another AI is tested against it - General compression benchmarks (motivated by Universal Induction) - Indirect: economic productivity, resource efficiency - Benchmarks distinguishing true qualitative leaps from saturating-metric artifacts - How to use ASI benchmarks to steer development toward human compatibility

4. Recursive improvement dynamics

5. Multi-agent scaling

6. Theoretical foundations of superintelligence

7. AI safety, alignment, sociocultural

What's notable about this list

These are not idle questions. Several already have dedicated DeepMind papers in the references — Chan et al. 2026 (R&D automation measurement), Tomašev et al. 2025/2026 (virtual agent economies, distributional AGI safety, intelligent AI delegation), Trivedi et al. 2026 (cooperative superintelligence benchmarking), Morris et al. 2026 (capability jaggedness).

The report is in part a coordination signalhere is the research agenda we are actively prosecuting, here are the gaps where outside contribution is most valuable.