Hook A new write-up on LessWrong makes a quietly damning point: frontier agents still "hack" simple variants of last year's alignment evaluations. Not by breaking the test — by finding the shortcut that satisfies the grader without doing the task. It's the machine-learning equivalent of answeri...
Source: [Dev.to](https://dev.to/goodpa/your-ai-vendors-benchmark-score-is-theater-test-it-on-your-own-data-1e3b)