A Set of Precise AI Capability Predictions
teortaxesTex · x · 2026-07-15
The author expresses respect for those willing to make precise predictions and shares a specific set of forecasts for AI evaluations and metrics.
Covering areas such as AA, CAIS TCI, CAIS RLI, SWE-Bench Pro, Terminal-Bench 2.1, CyberGym, MMMU-Pro, BabyVision, and CharXiv RQ, these predictions reflect a quantitative assessment of the evolution of AI capabilities rather than vague generalizations.
More from AGI Musings
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22
- AI Power Demand Exposes US Energy Gap, Urging Shift from Scarcity to Abundance — bradneuberg · 2026-07-22
- ControlAI CEO says an international ban on superintelligence is needed to avert extinction risk — zetalyrae · 2026-07-22
- Gary Marcus says LLMs still cannot really do math on their own — GaryMarcus · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- AI may make digital work infinitely leveraged while offline life gets more human — illscience · 2026-07-22