Garry Tan
2 Tools · 5 Intel
Garry Tan is a Canadian-American engineer and investor who studied computer systems engineering at Stanford, was an early employee at Palantir, and co-founded Posterous, one of the first well-designed blogging platforms, which Twitter acquired in 2012. He first joined Y Combinator in 2011 as a partner — contributing to internal tools and writing Coinbase's first seed check — before departing to co-found the venture firm Initialized Capital. He returned to YC as President and CEO in January 2023.
Is this you? Sign in with X to claim this profile.
Tools
Intel
A short essay arguing that productive AI coding agents come from a lightweight harness plus composable skills. Explains the context-management and workflow ideas behind the '10-100x' claim. An opinion piece, not a harness you can run.
LangSmith gives you trajectory evals, trace-to-dataset pipelines, model-as-judge and regression suites, but tools are not a practice: nothing tells you what to test, in what order, or when you are finished.
A follow-up on thin harnesses and fat skills, arguing that resolvers, the routing layer deciding which skill handles what, matter more than the skills that got all the attention, and are invisible precisely when they work.
Jepsen's Kyle Kingsbury, who spent a decade proving distributed databases broke their own consistency guarantees, turns the same methodical scepticism on language models.
Figma's Dylan Field and YC's Garry Tan discuss why current AI stays a 'tool' that widens exploration but hasn't closed the design-quality gap, and why craft and judgment still matter when models make prototyping nearly free.