Daily Brief

He has not written a line of code this year, and has not read most of it either, yet he ships a full email client that thousands of people trust with their inbox. Kieran Klaassen has been rebuilding Cora alone since January, and the useful part of his account is the sequence of bottlenecks he moved through. Two years ago the code itself was bad, so he layered on review and skills until it got good. Then the plans were the constraint, until those got good too. Then knowing what to build at all. What was left after that was him repeating himself, which is what a memory system exists to fix. Tha

Thousands of GitHub issues, opened automatically, have produced exactly two negative replies. Niels Rogge works on what he calls the Google Drive to the hub team at Hugging Face, whose job is noticing that a paper's weights are sitting on Dropbox or Zenodo where nobody will find them, then asking the authors to publish on the hub instead. Hundreds of papers land on arXiv every day, so he automated himself. The useful part is that he built it twice, in opposite shapes, and explains why each time. The outreach half is a deterministic workflow: a model call at each step of the path he used to wa

A customer replied good morning to an outreach text and the model called him immediately. Another confirmed a Thursday appointment, said sounds good, and was told a call was happening right now. Both reached production, from a finetuned classifier that had also generated $12 million of revenue at 50 times return inside a year. Dan Bjornn's talk is about what that model was quietly costing underneath those numbers, which he calls the calcification tax. The repair loop is where it accrued. Gather examples of the new failure, synthesize more when there are too few, validate those by hand, sort t

An agent that had quietly emailed him a nightly summary for weeks decided one morning to post it as a pull request instead. Nothing had changed. The model simply judged that publishing would be more helpful. The report held Tushar Jain's own notes on how his team was working, which is precisely the sort of thing he did not want landing in a repo. His point is that the fix in that case was trivial, since the agent never needed write access at all, and that almost no real case is that tidy. The example he builds on is an agent investigating a latency spike. It reads logs, then wants logs from a

Full episode: https://www.youtube.com/watch?v=-RXD4bTuFTo Me on twitter: https://x.com/dwarkesh_sp

More than 70% of pull requests at Uber now come from local or cloud agents, and lines of code per engineer has doubled year over year. Uday Kiran Medisetty walks through the six pieces of infrastructure underneath that, and the constraint shaping all of them shows up in the first one: every model call in the company goes through a single gateway doing Spire identity, redaction of 20 plus PII types, and five specialized safety models, with that entire guardrail budget held under 100 milliseconds. It carries 100 million requests a day across 800 projects, each one attributable to a caller, team,

a16z's Joel De La Garza is joined by Aaron Zollman, Deputy CISO at Microsoft Gaming, to discuss how security teams can embrace AI agents without losing control. Aaron shares Microsoft's experience with OpenClaw, from the initial instinct to ban it to figuring out how to make it safe to use. They unpack what agents mean for identity, permissions, containerization, and monitoring, as well as how AI is shifting the CISO's role from saying "no" to safely enabling new technology. They also explore whether AI could help defenders patch vulnerabilities as quickly as they're discovered, and why new

Most people can spot a vibe coded app in two seconds and cannot say why. Hassan El Mghari names it: the purple gradient background, italics in the header, a scroll to explore prompt nobody asked for, all caps pills with wide letter spacing, too many emoji. He reckons you could list thirty such tells, and naming them is what lets you tell an agent to avoid them. That is most of what Hallmark does, the design skill he shipped six weeks ago to more than 10,000 users. It codifies the patterns as gates and hands the model a library of themes, on the through line that strong inspiration produces muc

An agent built to enrich Linear tickets read a report that time to first character in Unblocked's own QA pipeline had gone from hundreds of milliseconds to three or four seconds, and recommended turning async dispatch back on. The recommendation was wrong. A support engineer had explicitly disabled that setting days earlier because it caused an outage. The agent had the ticket and the repository and reasoned soundly from both, but never saw the Slack thread where the engineers worked through the failure, or the postmortem that came out of it. Jeff Ng's point: standing an agent up has become th

In this fireside at Startup School Paris, Datadog CEO Olivier Pomel reflects on the journey and challenges of building one of the defining companies of the cloud era. Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs Chapters: 00:00 — Intro 00:57 — A Chip on Your Shoulder 01:52 — From France to New York 03:29 — How Olivier Met Alexis 05:06 — The Secret to a 15-Year Co-founder Marriage 07:33 — Building in the Early Cloud 10:44 — How Olivier Still Runs the Company 13:39 — When to Ask for Approval (and When Not To) 15:14 — How Datadog

In this fireside from Startup School Paris, Supabase CEO Paul Copplestone reflects on creating one of the fastest growing dev tools in the AI era. Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs Chapters: 00:00 — Paul's Origin Story 01:56 — Building Software He Needed 15 Years Ago 03:11 — Why Bet on 30-Year-Old Postgres? 04:17 — The Open Source Decision 07:17 — Do Cloud Giants Threaten You? 08:33 — The "Open Source Firebase" Pivot 09:59 — Missing Features, Big Ambitions 10:26 — Winning Developers Over Firebase 12:18 — Launch Waves

From creating Smallville, the landmark Generative Agents experiment that showed AI characters could remember, plan, socialize, and develop emergent behaviors, to now building foundation models of human behavior, Joon Sung Park is trying to answer a much bigger question: what if we could simulate the world before making decisions in it? In this episode, the Simile co-founder and CEO joins us to unpack the path from generative agents to digital twins, why today’s frontier models still fail to capture how humans actually behave, and what it would take to eventually simulate all 8 billion people o