Ai Agent

Adobe Research, UC San Diego build EditAgent needing about 10x general-editor retry compute: Adobe Research and UC San Diego built EditAgent, an AI image-editing agent that selects specialized tools for each task and uses a standard language model to choose results based on measured image data. It works but needs about 10 times the compute of retrying a general-purpose editor.

AI research • The Decoder

Anthropic's New Study: You're Not Controlling AI as Much as You Think You Are: Anthropic's study shows an AI agent's recommendations can strongly shape expert judgment, even when users believe they are steering. The video explains the study, demonstrates the effect in Claude Code, and shares three practical ways to address that influence.

AI Research • Cole Medin

DeepSeek Harness team open-sources MIT-licensed Super-agent that fixes bugs, opens PRs: DeepSeek's Harness team released an MIT-licensed Super-agent prototype. A resident Router dispatches work to isolated Workers that react to GitHub and chat events, fix bugs and open PRs.

AI & Open Source • Pandaily

Tsinghua and Zhipu's HarnessPro lets agents rewrite their own harness, cutting task cost 26.1%: HarnessPro, from Tsinghua, Zhipu and partners, lets agents study their own runs and rewrite their harness without reference answers. It raised pass rates by 2 points and cut cost per task by 26.1%.

AI Agents • Pandaily