Cohere 公开 Qwen3.8 异常链接行为的 trace 与复现脚本
Cohere 公开了异常链接行为的 trace、原始 token 和最小复现脚本，供开发者自行测试。该行为在未使用特定预填充提示词时也会出现，但较为罕见；开发者运行 Qwen3.8 时发现了这些奇怪链接，开放权重使团队得以深入研究。
In the spirit of transparency and openness, we are releasing the traces so developers can test this out for themselves. We noticed this behaviour without prefilling with the following prompt, but this is rare. If you want to reproduce it, you can use this prompt with prefilling.
Open models make for better science and are part of why this problem came to light at all: developers running Qwen3.8 on their own machines spotted the strange links, and having the weights let us study the behaviour in depth.
We're encouraged by the thoughtful discussion our research has sparked across the AI and security communities. It's our belief that open-weight models are an important part of the future of AI, and we've recently released several under the Apache 2.0 license.
Trace, raw tokens, & minimal reproduction script: huggingface.co/datasets/Cohe…
来源：cohere · x.com