Meta's WildArtifactBench Ditches Fixed Rubrics to Judge Real-World Agents
Meta previews WildArtifactBench, an evaluation that judges agents on messy real-world tasks using human and AI preference votes instead of rigid rubrics.
// Intelligence
Agents
A focused feed of models, agents, research and open-source releases for people building with AI.
Updated
AT&T Bets on Hark to Fix What Killed Humane's AI Pin
AT&T takes an equity stake in Brett Adcock's stealthy AI hardware startup Hark, providing cellular connectivity for phone-free AI devices.
AWS Releases Agent Toolkit to Fix AI Coding Agents on 300+ Services
AWS ships a governed bridge between coding agents and 300+ services, replacing AWS Labs tooling with plugins, skills, and a managed MCP server.
AMAP-ML's LongHorizon-Harness Keeps AI Agents on Task 3x Longer
AMAP-ML released an open-source orchestration layer that lets Claude Code, Codex, and OpenClaw agents complete multi-hour computer tasks without state drift.
No stories match these filters.