← RLVR

What podcasts say about RLVR

Every statement, with the speaker, the exact quote and the moment it was said.

What experts have said about RLVR

3 statements · 3 positive

  1. Dwarkesh PatelPositiveJun 26, 2026· Dwarkesh Podcast

    An extensively RLVR-trained AI could outperform LBJ’s political advice in 1948 Texas.

    “If you dropped this endlessly RLVR'd AI into Texas politics in 1948, it could give you better advice than LBJ about winning the Senate seat.”

    Listen at 6:27

    Open the episode · The next big breakthrough will be AIs learning on the job
  2. Dwarkesh PatelPositiveJun 26, 2026· Dwarkesh Podcast

    An RLVR-trained AI could build SpaceX with $100 million starting in 2002.

    “if you gave it a hundred million dollars in 2002 and let it cook, it would build SpaceX for you.”

    Listen at 6:35

    Open the episode · The next big breakthrough will be AIs learning on the job
  3. Dwarkesh PatelPositiveJun 26, 2026· Dwarkesh Podcast

    RLVR training produces agents able to navigate unfamiliar problems and iterate on strategies.

    “All of this RLVR training is producing an agent that can get its bearings when it's thrown at an unfamiliar problem, and it can try different strategies and it can iterate when it hits a roadblock.”

    Listen at 17:30

    Open the episode · The next big breakthrough will be AIs learning on the job

Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.