18 posts published in the last hour
- 14:37TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization
- 14:36SeVerus: Context-Aware, Gamified Benchmarking for Rust Verification
- 14:36Atomicwork Adds Six Certified AI Coworkers to Its IT Marketplace
- 14:36Multi-step SWE: Can Coding Agents Keep Building on Their Own Code Over Long Horizons?
- 14:35What I Did with Hermes Agent, Ollama & Local Models
- 14:35SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection
- 14:35Insilico Medicine Announces Open-Source Longevity Grok AI System
- 14:34Compositional Unalignment: Auditing Safety in Large Vision-Language Models
- 14:06More Agents, More Reliable? System-Level Reliability of Multi-Agent LLMs under Operational-Profile Uncertainty
- 14:06ToyBlocks: A controlled world for robot learning and evaluation
- 14:06Adapting LLM Judges to Observed Human Annotation Policy through Soft Prompt Tuning
- 14:05Amazon will let you text Alexa your shopping list
- 14:05Depth or Description? When a One-Step Latent Score Replaces Lookahead in Proactive Information Acquisition
- 14:05Atomicwork launches certified AI coworker marketplace for enterprise IT and security
- 14:04A Night at the LLM Zoo: Data Conditioned Flow Matching for Generating Pretrained LLM Weights
- 14:04METR finds Anthropic may have crossed its own AI acceleration warning threshold back in July
- 14:04Polynomial-Time Computation of Extensive-Form Proper Equilibria in Two-Player Zero-Sum Games
- 14:00AI News Brief Hourly Summary 2026-11-06 15h : 19 posts