MICROSOFT’S SKILLOPT SHOWS OPTIMIZED AGENT SKILL ARTIFACTS TRANSFER ACROSS MODEL SCALES AND BETWEEN CODEX AND CLAUDE CODE HARNESSES
REPORT A PROBLEM WITH THIS SOURCE
WHAT HAPPENED
Most coverage of Microsoft's SkillOpt centers on its 52/52 result. The more consequential finding is in Section 4.3: the exported best_skill.md keeps working in environments it was never trained on.
MarkTechPost reports that most coverage of Microsoft's SkillOpt centers on its 52/52 result.
The report adds: The more consequential finding is in Section 4.3: the exported best_skill.md keeps working in environments it was never trained on.
A Codex-trained SpreadsheetBench skill lifted Claude Code from 22.1 to 81.8, slightly above the 80.4 that harness reached training its own skill.
This report is covered across the current DAMMNEWS feeds. Technology stories often mix a product announcement with claims about availability, performance or impact. Those parts should be checked separately.
This is a developing report. DAMMNEWS will surface related coverage as closely matched reporting enters the live cache.
DAMMNEWS RSS BRIEFING — generated locally from the available MarkTechPost headline and RSS excerpt. It is not a summary of the full source article.
RELATED DAMMNEWS COVERAGE
- META AI RELEASES MUSE CODE (BETA): A TERMINAL CODING AGENT POWERED BY THE NEW MUSE SPARK 1.2 MODEL
MarkTechPost • 6 hrs ago • TECH - WHAT BTS’ GRAMMY BOYCOTT TELLS US ABOUT THE PROBLEM WITH ‘ASIAN POP’ AS A LABEL
Arts + Culture – The Conversatio • 16 hrs ago • CULTURE - WHAT’S THE BEST VEGETARIAN ALTERNATIVE TO GELATINE?
Food | The Guardian • 1 day ago • FOOD