A benchmark testing five AI models across 13 real Ruby codebases found that agents equipped with a structural code map achieved a mean cited recall lift of +0.26 for Claude Opus 4.8, with gains concen…
A developer building the code map tool Sense tested whether larger context windows and smarter models would eliminate the need for structural indexes in AI coding agents. Benchmarking five frontier mo…
An engineer building a benchmark for AI coding agents discovered that an LLM judge incorrectly scored a half-finished audit as 'exhaustive' because it lacked a reference answer. The judge evaluated th…
At Google I/O 2026, Google announced WebMCP, a proposed open web standard that allows developers to annotate JavaScript functions and HTML forms so browser-based AI agents can call them as structured …