News for hackers. Stuff that matters.
Re:DeepSeek-R1 by petra on Tuesday January 21, 2025 @01:20PM (#42783483)
You also need to be able to test your solution, on how sucsessful it is.

In some domains it is harder than math and code.

Re:DeepSeek-R1 by fsndz on Tuesday January 21, 2025 @04:13PM (#42785263)
true. I think simulations will help a lot in that direction. Imagine if you can do RL a bit like DeepSeek for R1 but on corporate tasks. https://open.substack.com/pub/transitions/p/deepseek-is-comi...