What happens when AI writes code humans can’t review?
Nothing is loaded from YouTube until you press play, and then without tracking cookies.
About this video
AI can already create codebases too large and complex for a human to reasonably review.
Formal verification changes the problem.
Define the properties that actually matter, then mathematically prove the system satisfies them.
AI can build at machine scale without requiring humans to trust it blindly.
#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
169 wordsCaptions as YouTube publishes them, usually machine-generated, so product and people names can be misheard.
- 0:00
I think from verification here is extremely helpful because it can it it allows you to create a very large code base, a very large product, right? And then a relatively small spec that you as a human actually is able to read. Prove it, right? And then and then you can say, hey, hey, AI created for me this massive thing that I wanted, right? It is way beyond my capability at this point to review it, right? But I want I cared about this, this, and this
- 0:25
property. And here I have formal proofs that the thing it built does satisfy the proof which is right. So I can use it. Right? So that will allow us uh to to trust AI in building much more complex systems that we can reasonably trust it today uh and still be certain uh that they are correct and uh effectively still be able to an extent inspect what is what is actually being created without without trusting it blindly.