Terminal-Bench

Everything Fervor AI has published that touches Terminal-Bench — 2 pieces, newest first.

• Terminal-Bench 2.1 vs 4.0: The Benchmark Version Number Is Now More Informative Than the Score

  When a model beats a rival on one generation of a benchmark and loses to it by twenty points on the next, the gap is the training target showing through, so the…

• Agent Training's Real Bottleneck Is Environments, and Terminal-Universe Says They Are Hiding in Your Traces

  The scarce input for agent post-training is executable environments rather than trajectories, and the tool-call history inside traces most teams already retain is enough…