Daily Brief

Deep dive into Prime Intellect's open-source ecosystem of post-training tools, including the verifiers and prime-rl libraries, as well as the Lab platform for self-serve training and inference. Speaker: Will Brown — Research Lead, Prime Intellect Will Brown leads Applied Research at Prime Intellect and builds open research infrastructure to enable every company to train, deploy, and self-improve their own frontier agentic models. He holds a PhD in Computer Science from Columbia University. X: https://x.com/willccbb LinkedIn: https://www.linkedin.com/in/willcb/ GitHub: https://github.com/wil

Sandboxes unleash agents by giving them secure, fully functional computers where they can tackle diverse tasks with minimal setup. This talk explores the architectural challenges of building an agent sandbox cloud. We compare runtime isolation technologies and their trade-offs, examine persistence and storage as the next major unlock for agent capabilities, and discuss the key decisions involved in orchestrating and scaling sandboxes. Abhishek Bhardwaj works on Agent and Reinforcement Learning Infrastructure at OpenAI. He builds systems that enable large-scale model training in RL environment

Full episode: https://www.youtube.com/watch?v=OS1NZLgKM2c Me on twitter: https://x.com/dwarkesh_sp

AI agents today execute on blind trust, and the failure modes are already in the headlines: a dealership chatbot agreeing to sell a $76,000 Chevy Tahoe for $1, a coding agent wiping a production database during a code freeze, an "agent skill" quietly installing a keylogger on a developer's machine. These are not edge cases. They are the predictable consequence of allowing agents to act without any mechanical guarantee of correctness or safety. Execution is irreversible. You cannot unsend a message, unwire a payment, or un-delete a database. In that regime, permitting an unsafe action costs f

In the last two years, models have gotten exponentially smarter. Two years ago they couldn't pass the bar. Today, top 1% of test scorers. And yet most agents still can't answer a simple business question correctly. You ship a demo that works. You deploy it. The business abandons it in a month. The missing variable is context: the business definitions, procedural knowledge, and operational norms that make a human expert valuable. Drawing on hundreds of production deployments, Prukalpa Sankar will break down what it actually takes to give agents contextual intelligence — and get them past the

# How Forward Deployed Engineering is done at Cursor **Location:** Forward Deployed Engineering / Room 2020 **When:** Day 2 - June 30, 2026 · 11:10am-11:30am ## Speakers ### Pauline Brunet VP, Forward Deployed Engineering · Cursor [LinkedIn](https://www.linkedin.com/in/pauline-brunet/) VP of Forward Deployed Engineering at Cursor. Building the motion and team to help customers adopt Cursor and drive meaningful returns. We configure and co-build alongside customer software and transformation teams. Spent 10 years in AI deployments across enterprises. — [View on the schedule](https://www.ai

There are thousands of agent skills. Almost none of them are tested. They get vibe-checked with two manual runs, maybe a thumbs-up from a colleague, then shipped. You wouldn't merge code without tests — so why are we shipping skills without evals? This talk covers the full lifecycle of building reliable agent skills: what a skill actually is (and isn't), how to write one that triggers correctly, and how to build a lightweight eval harness that catches failures before your users do. ### Philipp Schmid Staff Engineer · Google DeepMind [X/Twitter](https://x.com/_philschmid) · [LinkedIn](https://

Katelyn Lesse and Angela Jiang lead the team building Anthropic's developer platform - the layer that both outside builders and Anthropic's own products run on top of. Angela frames the platform as a three-layer stack: knowledge, execution, and coordination. She argues the real leverage is what’s at the top: "strategies," or meta-harnesses that give each token a different job, from advising to executing to reflecting to memory. On the question of open ecosystem vs. walled garden, they say they aren't precious about owning the stack. Katelyn points to Anthropic's self-hosted sandboxes with part

For his closing keynote, Addy Osmani explores the evolving role of software engineers in the age of AI agents. He argues that as coding tasks become increasingly automated, the true value of an engineer shifts from mere code production to accountability, judgment, and system ownership. https://addyosmani.com/ https://x.com/addyosmani/status/2074927530482835916 Timestamps 0:00 Introduction and the human side of engineering 1:46 Rebundling roles and ownership of systems 2:34 Harnesses, loop engineering, and software factories 3:34 The shift to answerability as an engineering requirement 4:26

In this episode, Engram co-founder and CEO Dan Biderman joins Allen Park cook Mediterranean meatballs with yellow rice and talk about building AI that actually learns from you: why long context, RAG, and compaction eventually break down, how Engram compresses knowledge into cartridges and model weights, what continual learning could unlock for long-horizon agents, why token efficiency is inseparable from intelligence, how personal models could improve like Tamagotchis, and what it takes to build the research and infrastructure for millions of continuously updated AI memories. Timestamps: 0:00