Patrick Jiang (@patpcj) introduced Harness 1, a 20B parameter search agent that moves search state outside the model and into a structured harness, according to a 13 post thread on X and the accompanying paper. The paper lists authors from the University of Illinois at Urbana Champaign, UC Berkeley and Chroma, and describes Harness 1 as a retrieval subagent trained with reinforcement learning inside a stateful search harness. The core claim is that search agents fail partly because they are a...
source & further reading
runtimewire.com — original article
Kilo Code AI says MiniMax M3 matched Claude Opus 4.8 on a code audit for $0.07
Markus Buehler frames AI discovery as a verified regime shift
Higgsfield AI's $500K feature film turns AI actors into a Hollywood test case