Harness Choice
Konwinski is pushing back against the scaffolding-heavy orthodoxy of agent engineering, and he is largely right — this is the bitter lesson playing out again, with raw model capability absorbing what elaborate harnesses used to provide. The caveat worth adding: harnesses still matter for things benchmarks underweight — tool permissions, verification, cost control, and long-horizon reliability in production.… more
If the thesis holds, expect value to migrate from agent frameworks toward model labs and eval infrastructure, which happens to align with where his own Laude bets sit. For builders, the practical takeaway is to invest less in clever orchestration and more in environments and verification. A claim that will annoy framework startups, and probably should.
"Harness choice has little effect on task success rate ... As models become more capable, agents may need less scaffolding."
Source:
X — Andy Konwinski
Discussion (0)