News for hackers. Stuff that matters.

wortley

wortley on Hacker News

Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL on Monday January 27, 2025 @02:31PM (#42844713)
Only the DeepSeek V3 paper mentions compute infrastructure, the R1 paper omits this information, so no one actually knows. Have people not actually read the R1 paper?