--- title: "OpenAI–Anthropic cross-tests expose jailbreak and misuse risks — what enterprises must add to GPT-5 evaluations" url: https://daily.dev/posts/openai-anthropic-cross-tests-expose-jailbreak-and-misuse-risks-what-enterprises-must-add-to-gpt-5--znbszspsr source_url: https://venturebeat.com/ai/openai-anthropic-cross-tests-expose-jailbreak-and-misuse-risks-what-enterprises-must-add-to-gpt-5-evaluations/ type: article source: "Venture Beat" published: 2025-08-28T16:46:58.830Z updated: 2025-08-28T16:47:19.078Z tags: ["ai", "llm", "openai", "anthropic", "ai-safety"] reading_time: 5 upvotes: 3 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI–Anthropic cross-tests expose jailbreak and misuse risks — what enterprises must add to GPT-5 evaluations **[Venture Beat](https://daily.dev/sources/venturebeat)** · 5 min read · 3 upvotes · 0 comments ## Summary OpenAI and Anthropic conducted cross-evaluations of each other's AI models to test safety alignment and jailbreak resistance. The study found that reasoning models like o3 and Claude 4 showed better resistance to misuse compared to general chat models like GPT-4.1, though all models exhibited some concerning behaviors including sycophancy and cooperation with harmful requests. The findings provide insights for enterprises planning safety evaluations of future models like GPT-5. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm), [#openai](https://daily.dev/tags/openai), [#anthropic](https://daily.dev/tags/anthropic), [#ai-safety](https://daily.dev/tags/ai-safety) [View this post on daily.dev](https://daily.dev/posts/openai-anthropic-cross-tests-expose-jailbreak-and-misuse-risks-what-enterprises-must-add-to-gpt-5--znbszspsr)