Daily Brief

*Note: Kenton has just released Cloudflare OS today: https://x.com/KentonVarda/status/2084990137180590572 This talk was recorded a month prior to launch.* Claude needed a strikethrough the slide app did not have, so it added one to the app. Asked to build a deck from a Google doc, it also added text centering and a box that accepts raw SVG, then generated the SVG for a diagram the app could not otherwise draw. That is Kenton Varda's argument in a single move. Software today ships from a developer to users whose feature requests die in Jira, and the escape hatch developers reach for is a plugi

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

Run terminal bench on Opus and on Haiku and Opus scores about three times better at a tenth of the cost, even though Haiku is far cheaper per token. Alex Atallah's point is that a small model pushed outside its training distribution thrashes, calling tools in loops until it costs more than the expensive model ever would. That inverts the obvious version of model routing, where you send each task to whichever model benchmarks best on it. Walden Yan calls that approach fragile for exactly the reason agents make it worse: a session starts as a question about a codebase, becomes a feature request,

At our inaugural YCML at Startup School, YC Partner Ankit Gupta speaks with Jitesh Jain about building video agents that can adapt their reasoning to videos of different lengths. Current agents often struggle with long, open-ended video questions because temporal grounding is unreliable and training data is expensive. SAGE combines visual tools with transcripts and web search, then uses synthetic question-answer data, tool trajectories, and reinforcement learning to teach the model when each source of information is useful. As videos become longer, the agent takes more reasoning steps and imp

At our inaugural YCML at Startup School, YC Partner Ankit Gupta speaks with MIT PhD candidate Jovana Kondic about ChartNet, an open-source data generation pipeline and million-scale dataset for chart understanding. Charts require models to combine visual recognition, text understanding, and numerical reasoning. ChartNet generates diverse examples by translating charts into plotting code, augmenting that code, and rendering new images with corresponding tables, summaries, and reasoning traces. Training on ChartNet improved open-source models across a range of chart tasks and transferred to rea

At our inaugural YCML at Startup School, YC Partner Ankit Gupta speaks with Mark Žnidar about predictive models that work directly with relational databases without flattening their tables or manually engineering features. The method represents a relational database as a graph, samples the relevant neighborhood around an entity, and uses specialized attention mechanisms to capture columns, features, and relationships across tables. This preserves information that is often lost in traditional tabular machine learning pipelines. Despite having only 22 million parameters, the model outperformed

At our inaugural YCML at Startup School, YC Partner Ankit Gupta speaks with Surgan Jandial about evaluating how web agents plan, rather than only measuring whether they complete a task. The work breaks planning into individual skills such as temporal ordering, future-state prediction, action selection, and error correction. It then repurposes existing datasets to create inexpensive synthetic tests that measure each skill independently. These scores correlate with agents' performance on complete web tasks, providing a cheaper and more interpretable way to identify their weaknesses before runni