Now I’m starting to learn large models. Many tutorials include
Now I’m starting to learn large models. Many tutorials include: adjusting the OpenAI API, setting up Transformers, making a RAG, and then connecting an Agent. Although things can run smoothly, how exactly Attention, Tokenizer, Pretrain, and SFT are connected is still a mystery in many cases. In the past few days, I have been looking for a project called MiniMind that is very suitable to fill this gap.
We've got Opus 4.8 at home!
Running DeepSeek V4 Flash Vision-Exp on 2 x DGX Spark with OMP. This is a mini-benchmark firmware analysis task I've been using to test out different models/harnesses. Opus 4.8 didn't find anything in this firmware that DeepSeek didn't. Thanks
GPT-5.6 SOL with DeepSeek Harness is insane at creating voxel dioramas.
AionUI is open source and runs locally on Mac, Windows and Linux.
Add a model key from OpenAI, Anthropic, Gemini, OpenRouter or DeepSeek and you can get started in minutes. But the built-in agent is only half the story.
You have reached the end of the archive
All of deepseek