Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published 6 days ago • 78
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2 Paper • 2502.03544 • Published 8 days ago • 37 • 5
Great Models Think Alike and this Undermines AI Oversight Paper • 2502.04313 • Published 7 days ago • 25
Great Models Think Alike and this Undermines AI Oversight Paper • 2502.04313 • Published 7 days ago • 25
Great Models Think Alike and this Undermines AI Oversight Paper • 2502.04313 • Published 7 days ago • 25 • 2
Representation Engineering: A Top-Down Approach to AI Transparency Paper • 2310.01405 • Published Oct 2, 2023 • 5
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning Paper • 2403.03218 • Published Mar 5, 2024 • 1