Ramanujan Machine

Since 2023 I lead the Ramanujan Machine Group at the Technion under Prof. Ido Kaminer, working on the intersection of AI and mathematics. The field is changing very quickly - AI models, symbolic tools (both external and our own libraries), vibe coding - and we apply it to explore mathematical spaces and algorithmically discover new formulas and conjectures.

I like to describe our work as "doing math like engineers", automating ingenuity.

Our recent projects include the "ASyMOB" benchmark for algebraic symbolic reasoning (blogpost, paper), "From Euler to AI" (blogpost, paper) - unifying hundreds of formulas for Pi throughout the centuries into a single Conservative Matrix Field (see video below), and "Unsupervised Discovery of Formulas for Mathematical Constants" - using dynamic convergence behavior to cluster 1.7 million unknown formulas and discover novel formulas for multiple mathematical constants - which we presented in Vancouver:

Created for the 3Blue1Brown "Summer of Math Exposition", where we reached the final round.

Evo.Do

Mid 2018 I left my role as CEO of Aperio Systems to start a new company: Evo.Do. We built autonomous AI-bots that tested and validated games, based on Reinforcement Learning algorithms. 

It’s hard to make sure that a complicated game or app works properly after every change, patch, design shift etc. It takes thousands of tests and weeks of tester-time to do a full validation. For many years developers tried automating the process via scripting - programming a set of actions that should take the app from state A to state B and validate that indeed we reached state B. Unfortunately scripted tests are very “brittle” - any small change can make the test fail (not reach the intended end goal), even if there was no bug introduced. Devs ended up spending more time maintaining and fixing tests than fixing the actual game, and most went back to manual testing.

Evo strived to combine the best of both worlds: the speed and accuracy of test scripts with the adaptivity and flexibility of human testers. The user defines the goal of the test (for example “make sure the key can be picked up”) and the bot learns on its own (through trial and error) how to achieve that goal:

The novel approach (patent pending) garnered some interest and we were accepted to the inaugural batch of Tel Aviv University backed Xccelerator program, where I gave a pitch during the closing ceremony:

And later got into the largest startup accelerator in the world: Y Combinator (AI cohort).

Where I pitched at the famous YC demo day:

Going through YC was a life-goal of mine - so I got to strike that off the list as completed :).