资讯

Microsoft’s Patch Tuesday: About 80 Vulnerabilities Patched

An elevation of privilege vulnerability in the Windows NTLM authentication protocol and a flaw in Office’s Preview Pain are ...
GitHub

Provider-agnostic, open-source evaluation infrastructure for language models

OpenBench provides standardized, reproducible benchmarking for LLMs across 30+ evaluation suites (and growing) spanning knowledge, math, reasoning, coding, science, reading comprehension, health, long ...