Funnel randomly assigned each new task in Reef, its internal data agent, to either GLM-5.2 (open weights) or Claude Opus 4.8. GLM averaged 7.8 seconds per model call against 18.1 for Opus.
In the News: October 28, 2026 (Extra 3)
Funnel's A/B test: GLM made 66% more tool calls than Opus and finished 14% slower. An interview study of two dozen engineers finds stock harnesses dominate.
Extra edition
Machine-readable
Download Markdown
Story
Funnel: the model with faster calls finished its tasks 14% later
Read story →
Story
Ilya Razenshteyn: interviews with about two dozen engineers find stock tools and human review
Razenshteyn interviewed what he calls a couple of dozen engineers and researchers, from frontier labs to finance to small start-ups, about how they use coding agents at work. He dropped a planned survey because the stories were too…
Hermit
An Apache 2.0 framework for training a "harness adapter", an external layer that adapts an existing agent without changing its model or harness. It lists GEPA, SkillOpt, MetaWorld Model, Harness² and Continual Harness as supported methods. The README's own demo says its score gain is constructed and "not a real-model performance result"; the per-benchmark results in the repository were not read. It had 292 stars when read.