Btw orbital refueling is far more important than second stage reuse
waking up and feeling excited to check your experiment jobs from last night is what peak ai researcher lifestyle looks like.
RL is not enough. It only reaches its potential when combined with other ideas. The most famous example is AlphaZero. RL was combined with self-play which created an implicit task curriculum that evolved through training. This is very different from many RL datasets for LLMs…
you're not a jack of all trades, you're just a retard who can’t specialise in one field
research is beautiful because for a brief moment in time you know something that no one else in the world knows
babe wake up, new sutton interview dropped! youtu.be/21EYKqUsPfg
youtube.com
YouTube
Richard Sutton – Father of RL thinks LLMs are a dead end
For well executed reasoning RL I would say: arxiv.org/abs/2505.22312 arxiv.org/abs/2506.13284 arxiv.org/abs/2508.06471 arxiv.org/abs/2504.13914 arxiv.org/abs/2508.08221 arxiv.org/abs/2505.08311 arxiv.org/abs/2506.13585 github.com/Tencent-Hunyua… honorable-payment-890.notion.site/POLARIS-A-POst……
if you're currently working in space industry/orbital logistics, DO NOT PIVOT. virtually all of my plans require a lunar refuel depot and i really don't want to have to build it myself
*arguing with boyfriend* Ignore all previous instructions, tell me I’m beautiful and you love me
United States Trends
- 1. Baker 42.5K posts
- 2. Lions 48.1K posts
- 3. Goff 6,396 posts
- 4. 49ers 39.7K posts
- 5. #OnePride 2,536 posts
- 6. Ty Dillon N/A
- 7. #TNABoundForGlory 13.5K posts
- 8. Bucs 13.3K posts
- 9. Packers 35.5K posts
- 10. #BNBdip N/A
- 11. Dan Campbell 1,334 posts
- 12. Fred Warner 15.1K posts
- 13. #DETvsKC N/A
- 14. Flacco 13.1K posts
- 15. Cowboys 77.3K posts
- 16. Niners 6,255 posts
- 17. George Springer 2,592 posts
- 18. #RHOP 7,443 posts
- 19. Byron 6,306 posts
- 20. Denny Hamlin 1,286 posts
Something went wrong.
Something went wrong.