What exactly did Irregular provide to Anthropic, test cases? I am so confused about this story.
Third-party cybersecurity evaluations. See, e.g., https://www.irregular.com/research/assessing-gpt-5.6-sol, which was published around the same time.
Third-party cybersecurity evaluations. See, e.g., https://www.irregular.com/research/assessing-gpt-5.6-sol, which was published around the same time.