alt Hacker NewsYes, but DeepSeek went absolute goblin-mode on optimization and I would not be shocked to discover that OpenAI and Anthropic were behind on that front.
Replies
Art9681 • today at 12:50 AM
OpenAI and Anthropic have more compute and the best frontier models to throw at the optimization problems. They have published articles on these efforts. For example, Dots, and Anthropic's upcoming "persistent agent" is because of these optimizations. Both companies often publish articles detailing a lot of their technical efforts. They just get buried among the flood of other news.
cactusplant7374 • today at 12:20 AM
What is the TPS of DeepSeek? All of the LLMs I have tried are slow as molasses. \
➕ show 2 replies
Yes, I would not be shocked either.
Sonnet 5.5 is 16x more expensive at $10 per million output tokens. Kimi K3.1 is also $10 per million output tokens, and its number of active parameters is only 6.5x larger than V4.1 Flash (104B compared to 16B). These things are not directly comparable of course, but just to give an idea.
Even if inference of those models needs 16x, 32x, or 48x the number of GPUs compared to V4.1 Flash, still seems like potentially great revenue per GPU.