11 posts published in the last hour
- 06:37ViBench 2.0: A Benchmark for Long-Horizon Software Building
- 06:37Anduin: A sybil-resistant agentic marketplace reputation system
- 06:36Verified but Vacuous: Three Failure Surfaces of LLM-Driven Verified Code Generation
- 06:36Assurance-Conditioned Continuous Authorization for Autonomous AI Agents
- 06:36[AINews] It’s Swapping Season
- 06:36Hybrid Spark: Adaptive Speculative Decoding That Lets the Content Choose the Drafter
- 06:06VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas
- 06:06Whose Transparency is it Anyway? Understanding Generative AI Transparency Needs and Gaps Across Stakeholders
- 06:06BrainBind: Bridging Synchronized EEG and fMRI through Long-Form Naturalistic Video Representations
- 06:06AGORA: Reliability-Aware Aggregation of LLM Judges via Item-Response Theory
- 06:05Iterated creation, grading, and revision of data science projects by language models