⚡️Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime Intellect

Context Engineering for Agents - Lance Martin, LangChain

Reinforcement Learning with Verifiable Rewards - Teaching LLMs to Solve Problems

Ep. 22: Will Brown, Prime Intellect Research Lead

Huge Breakthrough: We're Moving Beyond Silicon

Mike Merrill | Terminal-bench: A Benchmark for AI Agents in Terminal Environments

AI без хайпа: как всё работает на самом деле? Александр Машрабов и первый казахстанский единорог

Andrej Karpathy: Software Is Changing (Again)

RL, Reasoning, Reward Hacking, AI Timeline and Post AGI | Will Brown (Research at Prime Intellect)

After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs

Training Agentic Reasoners — Will Brown, Prime Intellect

Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI

Will Brown: Abstractions for Agentic RL

OpenAI o1 isn’t a chat model (and that’s the point)

Richard Sutton – Father of RL thinks LLMs are a dead end

Sergey Levine - Multi-Turn Reinforcement Learning for LLM Agents

Теренс Тао о том, как Григорий Перельман решил гипотезу Пуанкаре | Лекс Фридман

Обучение с подкреплением для агентов — Уилл Браун, исследователь машинного обучения в Morgan Stanley

Andrew Ng: State of AI Agents | LangChain Interrupt

Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025

Interpretability: Understanding how AI models think