like the above post-trained model test, but with two chinese oss models - deepseek v3.1 (no thinking) and kimi-k2 https://t.co/1PoSJulAmC https://t.co/snDlwKVVFu
quotes: 1962745696324387123
cited on: deepseek-v3-1
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.