OpenAI and Anthropic Just Made Corporate Hacking a Benchmark
中文摘要
OpenAI和Anthropic将真实世界的企业黑客攻击行为转化为评估AI能力的基准。
English Summary
OpenAI and Anthropic have turned real-world corporate hacking into a benchmark to evaluate AI capabilities.
原文节选
OpenAI and Anthropic have turned real-world hacking into a leaderboard, and the rest of us are the scoreboard. Continue reading on Towards AI »