Re:Why I'm still bearish on LLMs after navier-stokes
by danielmarkbruce on Tuesday September 15, 2026 @07:42PM
(#49720358)
Doesn't really even need to look like it. If you can verify rewards, RLVR will optimize really really well. If you can't... it's a struggle. There are probably fewer fields where you can verify rewards than one might hope.
[ Parent
| on HN ]
Re:Why I'm still bearish on LLMs after navier-stokes
by skydhash on Tuesday September 15, 2026 @08:26PM
(#49720660)
> There are probably fewer fields where you can verify rewards than one might hope.
2 tasks I've done today that I believe robots are nowhere near being able to do: Cleaning my wardrobe and draining bad fuel out of my generator. As in generic use cases.
Re:Why I'm still bearish on LLMs after navier-stokes
by danielmarkbruce on Wednesday September 16, 2026 @01:34PM
(#49730357)
Hard to verify that your wardrobe is clean. Also hard to verify that the bad fuel is out without physical sensors. Many, many tasks are quite difficult to verify beyond "you know it when you see it". That doesn't work so well for training a model.