Recently, I have been unwell with a gastrointestinal flu for several days, but I am feeling better today and can update on the recent hot topics related to DeepSeek. I won’t go into much detail about the specific news regarding DeepSeek, but on New Year’s Eve, they launched Janus-Pro, and various media outlets have been … Read more
Introduction We introduced our first-generation reasoning model DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero is a model trained through large-scale Reinforcement Learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrating exceptional performance in reasoning. With the emergence of RL, DeepSeek-R1-Zero naturally exhibited many powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero faced challenges such as endless repetition, … Read more
Yesterday, a friend noted that it performed even better than OpenAI-O1! I tested DeepSeek R1, and the conclusion is just two words: impressive! I was asked if DeepSeek-R1 can be used in Cline? Today, at the request of a friend, I will do a simple test. The task this time is to create an AI … Read more
* Click the blue text above “Niupitang Does Not Brag” to follow me Hello everyone, I am Niupitang! Recently, the domestic AI large models have been booming, with various manufacturers open-sourcing large models, especially the release of DeepSeek-R1, which has attracted widespread attention. This domestic AI model not only performs excellently in reasoning and code … Read more
Version 3.2 of cline has been released, featuring the Plan & Act Modes which effectively distinguish between AI code thinking and action, highlighting the capabilities of cline’s ‘System Two’. Planning Mode Optimized for situational collection and strategy Collaborates with you to formulate plans; does not write code Complete document reading capability for project understanding Focuses … Read more