What if the harness matters as much as the model itself, both for how many tokens you burn and how often you actually solve the task?
That’s the question @iamnamanvats and @oleg_golev explore in “The Scaffold Effect in Coding Agents”, accepted at the incoming @icmlconf 2026.
Here's how to use Sentient’s findings to cut your own coding agent's inference costs by up to 40x, and why your choice of harness may matter more than your choice of model ↓
For Shubham (@musickeeda), Arena meant sharing a room with other teams and chasing better results together, even as competitors.
That's what open-source AI hackathons make possible ↓