Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
zerosizedweasle
3 months ago
|
parent
|
context
|
favorite
| on:
CS234: Reinforcement Learning Winter 2025
Given Ilya's podcast this is an interesting title.
actionfromafar
3 months ago
|
next
[–]
So, basically AI Winter? :-)
airspresso
3 months ago
|
parent
|
next
[–]
That's how I read it XD "oh no, RL is dead too"
TNWin
3 months ago
|
prev
|
next
[–]
I didn't get the reference. Please elaborate.
egl2020
3 months ago
|
parent
|
next
[–]
Karpathy colorfully described RL as "sucking supervision bits through a straw".
apwell23
3 months ago
|
parent
|
prev
|
next
[–]
he said RL sucks because it narrowly optimizes to solve a certain set of problems in certain sets of conditions.
he compared it to students who win at math competition but cant do anything practical .
kgarten
3 months ago
|
prev
[–]
Which podcast?
ontouchstart
3 months ago
|
parent
[–]
https://www.dwarkesh.com/p/ilya-sutskever-2
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: