Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-07-16 · source-backed
Lilian Weng's harness engineering survey reports that the ability to propose harness improvements doesn't scale with model size. The bottleneck is utilization, not generation. That's an immediate cost lever: route harness-edit proposals to a cheap model and reserve frontier capacity for judging and applying them. The survey also notes harness improvements transfer across benchmarks, implying they encode reusable engineering patterns rather than benchmark-specific tricks, so a harness tuned on one task family is worth porting rather than rebuilding.
Each link below shares sources, entities, or timing with this story.
Claude Code uses Opus / Shared entity: Opus / Shared topic / Earlier coverage / Tension
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (cost, model).
Claude Code uses Opus / Shared entity: Opus / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (benchmark, capability, model).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (cost, engineering, model).
Claude Code uses Opus / Shared entity: Lilian Weng / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Lilian Weng; overlapping topics (engineering, harness).
Claude Code uses Opus / Shared entity: Opus / Shared topic / Earlier coverage
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (doesn, model).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (benchmark, model).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (cost, model).
Linked by a graph relationship (Claude Code uses Opus); both cover Opus; overlapping topics (cost, model).