Harness design

Week 43 · 19-25 Oct

1 source filed · EN 1

  • C

    Agentic Monitoring

    Change-point monitoring has been hard to adopt: well-run teams gain little, while blanket monitoring of noisy health metrics produces alert fatigue.

    50% / 30%heap savings and latency reduction found in a hot-path library by a few agent investigation sessions (one anecdote)

Week 42 · 12-18 Oct

1 source filed · ZH 1

  • C

    Huawei Noah's Memento 3 clears ARC-AGI-3 public set

    Full score of 100 RHAE on the public set, with 7,518 actions versus 17,135 for humans (about 56% fewer) and 8,347 for the previous best entry, Sergey Rodionov's baseline1 at 99.

    7518 vs 17135actions Memento 3 needed to clear all 25 ARC-AGI-3 public games versus the human total

Week 41 · 5-11 Oct

1 source filed · EN 1

  • B

    Why Are Coding Agents So Dumb?

    Lynch started with coding agents in February 2025 and expected agents to catch up with the models within six months; he says they did not.

    10subtasks OpenCode created for a 1.5k-line feature, then ran one by one