Reinforcement learning

Oct 09, 2026

Beam: The Great American Open Model with ReflectionAI Co-Founder and CEO Misha Laskin

Misha Laskin, co-founder and CEO of Reflection AI, discusses the company's 500B open-weight reasoning model Beam, the economics of frontier training, the shift from renting to owning intelligence in enterprise, the role of Chinese open models in the global ecosystem, and the case that openness itself is a safety strategy. He also reflects on how AI is accelerating scientific research and reshaping research team sizes.

Oct 08, 2026

AI Scientists Are Here: Autonomous Labs & Synthesis Superintelligence — Periodic Labs

Liam Fedus and Ekin Dogus Cubuk of Periodic Labs explain why scientific discovery requires physical experiments rather than more internet data alone, and how they are building autonomous labs where AI systems reason under noise and uncertainty. The conversation covers reinforcement learning grounded in experiments, the materials discovery loop from prediction to synthesis to characterization, the limits of DFT, why physics remains unsolved, negative results as training data, scaling autonomous labs, and the broader goal of synthesis superintelligence aimed at discovering new superconductors, magnets, and batteries.

Oct 07, 2026

Why Reflection AI Is Making the Open Intelligence Bet - and What It Means for Deploying Models

Joe Spisak of Reflection discusses why open models and open intelligence matter, covering RL-driven customization, environments as the new dataset, the OpenEnv project, PyTorch and Llama lessons, inference scaling, and the case for ecosystem control and open safety.

Oct 05, 2026

Your LLM Judge Is a Confident Liar: Building Better Verifiers — Browserbase

Browserbase and Microsoft Research unveil their Universal Verifier for computer-use and web agents, addressing the critical flaw of inaccurate LLM-as-judge benchmarks that yield "confident liars." They detail its four guiding principles, demonstrating how it drastically cuts false positives and provides high agreement with human evaluations, leading to better training data. An auto-research experiment highlights the synergy between AI and human expertise in developing robust evaluation systems.

Oct 02, 2026

What If We Stopped Using GPUs? | YC Paper Club

A session on alternative compute covering the argument for abandoning backpropagation in favor of zero-order optimization and sharded training, optical computing that performs diffusion-style image generation with propagating light, the state of neuromorphic computing in 2026, and how cultured human neurons learned to play Doom through reinforcement learning.

Oct 01, 2026

Better AI Starts With Better Verification

Halluminate, a Y Combinator S25 company, builds RL environments and benchmarks that teach AI models to do non-coding knowledge work, starting with financial services. In this fireside with YC Partner Jon Xu, co-founders Jerry Wu and Wyatt Marshall trace their pivot from evals to training environments, explain why verification quality matters more than task volume, and outline a roadmap toward multi-agent simulated companies. They also address reward hacking, alignment as an industry-wide responsibility, and what they look for in new hires.