Re:An analysis of DeepSeek's R1-Zero and R1
by Cthulhu_ on Thursday January 30, 2025 @03:33AM
(#42876042)
ChatGPT came out and its interface was a chatbox and a thumbs up / thumbs down icon (or whichever) to rate the responses; surely that created a feedback loop of learning, like all machine learning has done for years now?
[ Parent
| on HN ]
There are no comments on this comment yet.