I agree in a way, but then in that case Gemini Claude and Qwen are all derivations of each other and shouldn't be in the competition either.
DeepSeek did some studies on distillation, which might be what OpenAI is complaining about. But their bigger model is not a distilled version of OpenAI's.
To me the big question (which HN can't be bothered to discuss because SaM aLtMaN iS bAd) is whether DS shows that OpenAI can be done cheaply, or just copied cheaply. Your last sentence tells me you think DS built this from scratch. I haven't seen evidence of that.
DeepSeek did some studies on distillation, which might be what OpenAI is complaining about. But their bigger model is not a distilled version of OpenAI's.