DeepSeek V4 Pro

Yes it is. Once the codebase grows in size and complexity, the model becomes much less forgiving with vague prompts and demands accurate, detailed specs and a lot more review and testing at the end. Glad to hear that it is working well for you.

It is not bad enough for me to stop using it

The paper is here: [0] Was expecting that the release would be this month [1], since everyone forgot about it and not reading the papers they were releasing and 7 days later here we have it. One of the key points of this model to look at is the optimization that DeepSeek made with the residual design of the neural network architecture of the LLM, which is manifold-constrained hyper-connections (mHC) which is from this paper [2], which makes this possible to efficiently train it, especially with its hybrid attention mechanism designed for this. There was not that much discussion around it some months ago here [3] about it but again this is a recommended read of the paper. I wouldn't trust the benchmarks directly, but would wait for others to try it for themselves to see if it matches the performance of frontier models. Either way, this is why Anthropic wants to ban open weight models and I cannot wait for the quantized versions to release momentarily. [0] https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main... [1] https://news.ycombinator.com/item?id=47793880 [2] https://arxiv.org/abs/2512.24880 [3] https://news.ycombinator.com/item?id=46452172

At deepseek v4 pro api prices - this is fantastic. The whole thing costed approx 1$