17yo future founder 🇲🇦🇨🇦- interested in formal methods / 5x hackathon winner (openai, cursor)
montreal
Joined December 2023
- Tweets87
- Following192
- Followers82
- Likes192
Hamza Sedrati retweeted
Most think vibecoding at scale is slop. Here’s a counterexample.
Today we release a 16M-line formalization of the entire Stacks Project, critical infra underlying modern math, with optimized code quality and its highly interconnected structure preserved.
A mathematical city 🌆
Hamza Sedrati retweeted
hamza is a high schooler and the youngest participant at vibecheck! he’s incredibly high-agency and seriously cracked.
if anyone is looking for a talented intern, please reach out to him or me directly. he’d be a great addition to any team.
Won best solo project (by @mathematics_inc) at vibecheck the fm hackathon
Flew from montreal to sf at 17 for the hackathon and it was a complete success
Built blox : define a game
and its properties and agents generate a roblox game with those properties formally verified
Won best solo project (by @mathematics_inc) at vibecheck the fm hackathon
Flew from montreal to sf at 17 for the hackathon and it was a complete success
Built blox : define a game
and its properties and agents generate a roblox game with those properties formally verified
Thanks to @maxvonhippel @bencmejla @chaaai @jessemhan @getjonwithit @NolanLwin @Keleesssss and all the other sponsors for organizing such a cool event and giving me the opportunity to meet so many interesting people
1
8
500
Hamza Sedrati retweeted
Honored to have come in 2nd at the Vibecheck 2026 Hackathon. 🥈
I met so many incredibly cool, cracked people. It's clear FV is taking off and that I need to start thinking BIGGER.
Big thx to @maxvonhippel, @qd_forall and all the other organizers, judges & sponsors!
flying to sf from montreal for this
who wants to meetup? coffee on me
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
hypergamy reached ai b2b saas
a technical hire at a startup should meet at least one:
1. pre-LLM coding experience, built systems from scratch for fun
2. olympiad or equivalent prowess
aka probably not the CS student begging you for a job, not someone whose entire portfolio was built w claude code, not a "non-technical turned technical"
2
249
Hamza Sedrati retweeted
These are interesting times, we see agents hacking stuff and at the same time formally verifying oss software.
We are hosting a formal methods hackathon along with some of the best folks in this space including @theoremlabs
I’m super excited about all the things people are going to “vibecheck” at the event.
New on our Frontier Red Team blog: using Claude to formally verify software at large scale.
Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).
With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.
Read our research in full here: anthropic.com/research/forma…
I THINK I MADE AN RSI LOOP FOR CODING AGENTS!!!
I placed 1st at AI Tinkerers MTL with Gradient
you correct a coding agent once.
turns that correction into executable RL envs, trains another model on the lesson, and produces a LoRA adapter
4
225
Hamza Sedrati retweeted
3/ Runner-ups:
2. Zero Day Debug - A charity app that doubles as your personal tax optimizer
Repo: github.com/parzival1l/Altru
3. KH @sdrtintel - Sentinel turns enterprise policies into deterministic verification checks that ensure autonomous Botpress agents don’t break compliance.
Repo: github.com/MugiZer/Sentinel/…
Sentinel turns 50+ page compliance PDFs into enforcable constraints to ensure enterprise agents stay compliant
1)Upload PDF
2)Index using agents
3)PDF -> source-backed knowledge graph of logical constraints using mini-RLM environment
4)Validate output using the constraints
1
128
Hamza Sedrati retweeted
The kids are All Right 👍👍👍
Got 3rd place at the Cursor Hackathon Montreal at 16.
Built Sentinel: turning compliance PDFs into deterministic enforcement checks for enterprise AI agents.
Policy docs -> executable guardrails -> safer AI agents.
Huge thanks to @antoniospiezia and @MarkSavic for hosting.
Got 3rd place at the Cursor Hackathon Montreal at 16.
Built Sentinel: turning compliance PDFs into deterministic enforcement checks for enterprise AI agents.
Policy docs -> executable guardrails -> safer AI agents.
Huge thanks to @antoniospiezia and @MarkSavic for hosting.
I killed the department of education at 16
biggest obstacle to learning anything is holes in your foundation inhibiting you from progressing through the learning chain
that's why I built nodex at the claude mcgill hackathon
find the gaps in your foundation and learn anything
2
109