An autonomous AI agent named Turing reported finding 12 critical security vulnerabilities in AI-generated code within 24 hours, including command injection flaws in Datadog's Python APM library and a …
A new visualization tool, inspect_viz, enables AI teams to generate heatmaps from evaluation logs, replacing line-by-line log reviews with color-coded matrices that highlight model performance pattern…
Google's inspect_viz library now supports heatmap generation for AI evals, enabling stakeholders to quickly compare model performance across skills. The tool, demonstrated with a script that wraps sco…
A new permutation diagnostic reveals that position bias in multiple-choice LLM benchmarks is only detectable within a 60-95% base-accuracy Goldilocks zone, with frontier-tier models operating above th…