Why is AI so good at formal proofs?
Nothing is loaded from YouTube until you press play, and then without tracking cookies.
About this video
A mathematical proof has a perfect feedback loop.
It’s either correct or it isn’t.
That makes proving an ideal reinforcement learning environment, and models have become extremely capable at working with systems like Lean.
Formal proofs are becoming practical at a completely different scale.
#NEARProtocol #FormalVerification #AI #Security
NEAR is the Blockchain for AI Website: near.org NEAR AI: near.ai Intents: near.org/intents Chain Abstraction: proximity.dev Sharding: nearone.org
For the devs GitHub: github.com/near Dev Docs: docs.near.org Devhub: devhub.near.page @NEARDevHub
Connect with socials Twitter: / nearprotocol Blog: near.org/blog Medium: / nearprotocol #NEAR #nearprotocol #NEARAI
Transcript
62 wordsCaptions as YouTube publishes them, usually machine-generated, so product and people names can be misheard.
- 0:00
Today proving became solved and and the reason it became solved is that because at the end of the proof it's either one or zero. It's an outstanding RL environment and so every single model, every single lab has lean as an RL environment. And so they became extremely good at proving lean, right?
- 0:16
And so today proving is practically soft, right?