What Today’s Best Models Still Can’t Do in Math

Gives a practitioner's view of where frontier models fail autonomously but succeed with guidance, a pattern that applies to how you scope work for coding and research agents.

• videoInside the Race to Measure Frontier Intelligence
• videoDeepSeek, Reasoning Models, and the Future of LLMs
• videoIs AI Slowing Down? Nathan Labenz Says We're Asking the Wrong Question
• videoWhy Scale Will Not Solve AGI | Vishal Misra - The a16z Show

• videoInside OpenAI’s Breakthroughs in Mathematical Reasoninga16z
• videoWhat happens now that AI is good at math? — the OpenAI Podcast Ep. 17OpenAI
• videoGrant Sanderson (@3Blue1Brown) – AI disproved a famous math conjecture. Now what?Dwarkesh Patel

Checking sign-in…

Loading comments…