Same model, different harness: task completion rises from 30% to 81%

A controlled test ran three agent harnesses (CUGA, Hermes, Deep Agents) with the same open-weight GLM-5.3-flash model on 90 AppWorld tasks; changing only the harness moved task completion between 30% and 81%. The article argues enterprise use cares more about enforced rules and in-boundary deployment, the focus of IBM's open-source CUGA.

• Nous Research raises $90M Series B at $1.5B valuation2026-10-07
• Tech leaders adopt Trump's "Super Intelligence" rebrand of AI2026-10-30
• Paper argues AI is changing the value of a college degree2026-10-30
• IBM ships Granite Switch 4.1.1 patch release2026-10-29
• IBM launches IBM Z Atlas system intelligence offering2026-10-27