12 posts published in the last hour
- 11:33Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations
- 11:33The Past and Future of AI Scientists
- 11:33Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons
- 11:33AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
- 11:33New policy ideas for the Intelligence Age
- 11:33LLMs Don’t Pay for the Jump
- 11:03Disentangled Shared Representations Improve Morpho-Transcriptomic Integration
- 11:03Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
- 11:03ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond
- 11:03Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
- 11:03Designing Sustainable Federated Learning as a Service using Neural Architecture Search
- 11:00AI News Brief Hourly Summary 2026-08-17 13h : 13 posts
