News for hackers. Stuff that matters.
Re:An analysis of DeepSeek's R1-Zero and R1 by vanviegen on Thursday January 30, 2025 @02:34AM (#42875749)
They're not actually processing the entire system prompt (which is rather long) on every query, but continuing from a model state saved after processing the system prompt once.

That makes it a bit harder, but still, spitting out the wrong date just seems like a plain old time-zone bug.

There are no comments on this comment yet.