Sarthak
writing RSS

Writing

Evidence-backed notes on agent harnesses, evaluation, and verification — directional case studies, not leaderboards.

2026
Jul 11, 2026

Don't judge an agent by its pass@1

A single pass@1 score collapses runs that differ on three axes it can't show: how a failure was shaped, whether a success repeats, and what either one cost. One model concluded a secret-safety task in 4 turns; two others avoided the leak but never concluded, burning ~77× the tokens. Then the reliability metric I reached for turned out to move in coarse sixths, and inverted when I reran the identical matrix. What to log, and how far to trust it.

Jul 1, 2026

Is your harness driving your model crazy?

One model went from a 0.10 to a 0.75 success rate without anyone touching the model. The fault was a tool-schema bug in the harness, and the only reason I caught it was reading the agent's trajectory instead of the scoreboard. A case study on why agent evals score the whole system, and how to tell which part you're actually measuring.

Jun 18, 2026

When is an agent truly done?

Many agent loops still treat a model's completion message as terminal, but stopping isn't the same as being correct. On moving the authority for 'done' out of the model and into a verifier, and what that one move makes measurable.

© 2026 | Sarthak
  • github
  • linkedin
  • email