
I build and teach AI • AI/ML @togethercompute • EngSci ℕΨ/PhD @UofT • Previously: vector DBs, data scientist, lecturer & health tech founder • 🇺🇸🇨🇦🇵🇰
San Francisco
Posts tracked from 11/16/2023 to 4/8/2026
Posts Analyzed
259
Platforms
3
Total Followers
5,201
Positive Sentiment
55%
142 positive of 259
they tested sota LLMs on 2025 US Math Olympiad hours after the problems were released Tested on 6 problems and spoiler alert! They all suck -> 5% https://t.co/dDH2s2IEt5
The post reports that state-of-the-art LLMs performed poorly on the 2025 US Math Olympiad problems.
Planck
ai-insurance