News for hackers. Stuff that matters.

A comment on DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL. Parent comment

Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs v... by dr_dshiv on Saturday January 25, 2025 @03:07PM (#42824366)
This explains so much. It’s just malice, then? Or some demonic force of evil? What does Occam’s razor suggest?

Oh dear

[ Parent | on HN ]
Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs v... by layer8 on Saturday January 25, 2025 @03:15PM (#42824442)
Always attribute to malice what can’t be explained by mere stupidity. ;)
[ Parent | on HN ]
Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs v... by pjc50 on Saturday January 25, 2025 @03:31PM (#42824585)
You missed the really obvious sarcasm.
[ Parent | on HN ]
Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs v... by nejsjsjsbsb on Saturday January 25, 2025 @08:50PM (#42826938)
Never a true a word as said in jest
[ Parent | on HN ]
Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs v... by buryat on Saturday January 25, 2025 @03:21PM (#42824497)
payback for Opium Wars
[ Parent | on HN ]