rico ☻

"hard questions are great but only if we deem you worthy enough to not silently downgrade you, or even get access at all"

Models out of the box have trouble reviewing DoorDash’s codebase, even when feeding them appropriate context. Single-pass AI reviewers only caught 30% of the real issues in our PRs. Instead, we built a multi-model (Sonnet 4.6 + Opus 4.8) code review agent that caught 53.6% issues at $3.91 a PR (most enterprise code review solutions perform significantly below 50% recall on DoorDash PRs). Today, we’re proud to share DashBench, our internal benchmark to compare multi-model/harness code review systems against each other. DashBench has given us confidence in maximizing the intelligence per dollar we’re spending on AI tokens to ship code safely.

🧠⌨️ Decode language from brain activity without surgery. 🧠⌨️ Brain2Qwerty V1 is officially published in Nature Neuroscience. Today, we're releasing Brain2Qwerty V2. We achieve unprecedented performance for a non-invasive MEG setup. Details below 🧵👇

We’re winding down the Notion Mail inbox across web, desktop, and iOS on September 22. We launched Notion Mail with a belief that your inbox should think like you—more personal to how you work and over time, more capable with AI. As Notion agents have gotten more capable, we’ve seen more users hand off email workflows to them. Today, more than half of Notion Mail users manage emails without ever opening their inbox. So, we’re going all in on using agents to run your inbox. We’re grateful to each and every one of you for building your routine around Notion Mail and trusting us with something that mattered as much as your email. More to come! The Notion Mail Team.