Using AI and formal reasoning to break hard math problems
Dublin
- Tweets 58
- Following 56
- Followers 693
- Likes 31
Excited to share a new podcast, this time with Fabrizio Montesi, Professor of Computer Science at SDU and lead maintainer of CSLib (Lean library for CS)
We kept landing on a question most AI code talk skips: we can prove software correct, but correct against what?
Thread👇
3
5
1,081
Latinum Frontier Mathematics Research Lab retweeted
🏅 @LatinumAI (Honourable Mention)
Smart contracts are still mostly secured through informal reviews and expensive audits, leaving critical bugs to slip through.
Latinum solves this with a formal verification toolchain that compiles Lean 4 to Solana SBF, proving contract properties at build time before code can ship.
Their demo shows a verified vault contract deployed onchain, with the compiler refusing to build when a balance leak is introduced.
In short: they’re making it possible for @solana developers to write contracts that can mathematically prove they work before they go onchain.
1
1
5
171
Latinum Frontier Mathematics Research Lab retweeted
Ireland takes home TWO winners and one honourable mention from @colosseum!
🏆 Grand University Award: @iochaindev - a decentralized AI inference marketplace (@Ericxin123)
🏆 @MentionedMarket - a social prediction market to trade words that get said across any form of media (@taylorferran & @Murraymiint)
🏅 Honourable mention: @LatinumAI - using LEAN programming language to write smart contracts on @solana
🏅 Shoutout to Superteam IE member @YellowFishZ on @craftsdev's W also.
Small country, big at heart 💚
@solana @superteam
1/ Announcing the winners of the Solana Frontier
Hackathon!🏔️
Read about the winners & honorable mentions: blog.colosseum.com/announcin…
The subset of winning teams accepted into our VC fund's next accelerator cohort will be shared in the coming days.
Congrats to all! 🏆
19
14
57
3,956
Why are formal languages not used as programming languages?
Most were built only for mathematics. Lean lets you write real code, but its compiler assumes a garbage collector, threads, and an operating system underneath.
So I rewrote it.
5
2
26
2,733
Why this matters for AI:
Today, people prompt Claude Code. It needs supervision, fakes tests to pass, bugs slip through.
1
5
770
Excited to share a new podcast, this time with Fabrizio Montesi, Professor of Computer Science at SDU and lead maintainer of CSLib (Lean library for CS)
We kept landing on a question most AI code talk skips: we can prove software correct, but correct against what?
Thread👇
3
5
1,081
Just released a podcast with @AlexKontorovich, Distinguished Professor of Maths at Rutgers. He has also been a forward looking thinker on how mathematics will evolve alongside AI. He has shared his forklift analogy for AI & learning here before, but it’s too good to not reshare!
3
8
3,614
Full Episodes:
Youtube:
piped.video/watch?v=m5CPceIb…
Spotify: open.spotify.com/episode/5U4…
1
243
On the maths community and AI startups:
"We're very non-confrontational as a culture. If someone is claiming things and you don't agree with them, you just don't invite them to your next conference. What we as mathematicians need to do is not just play defence."
1
145