Skip to content
Launchpad Library logo

epoch ai

2 free resources on this topic. Everything here is free and hand-picked. You can also search within this topic.

epoch.ai
Free
Research Paper
Research & Papers

Can AI automate AI R&D yet? (InnovationEval)

Epoch AI's early results from InnovationEval, published October 7, 2026. Epoch reports that the two frontier models tested, Claude Fable 5 and GPT-5.6 Sol, fell far short of the original human-developed technique and that their write-ups overstated their results.

#AI#AI research#evaluation#Epoch AI
epoch.aiAdded Oct 8, 20260 opens
epoch.ai
Free
Report
Research & Papers

Can AI Spot Mistakes in IKEA Assembly?

Epoch AI report on a spatial reasoning benchmark built around finding mistakes in photos of partially assembled IKEA furniture — a proxy for economically important visual reasoning tasks like repair work. Top scores jumped from 28% to 80% in 10 months; Chinese open-weight models trail the frontier by about 7 months.

#ai-research#benchmarks#spatial-reasoning#epoch-ai
epoch.aiAdded Sep 28, 20260 opens