Sparse Thoughts

i recently became somewhat obsessed with the jagged frontier in llm capabilities (and i have only Omar Khattab to blame for it). i want to try and make that “jagged frontier” argument a bit more concrete to what i can attest to (which is mainly health), b…

this post accompanies the PhenoBench preprint. also see the public repo and website and leaderboards. a while back i wrote about data activation: how we can use the data we collect and organize with great care to inform and improve AI systems. we have inc…

lately i’ve been busy with work. being in the sweaty, humid summer often leaves little reason to leave the comforting AC for the humid outdoors. naturally, this meant i was spending more and more time with the agents. i know i’m not the first to write this

over the past month or so, i’ve struggled to find the time and headspace to write properly. i’ve been knee-deep in a new and exciting project, hopefully more on that soon. i’ve still been reading, but mostly things that didn’t feel like they belonged here.

give me an optimizable metric and i’ll move the world. benchmarking, i.e., the act of building and applying benchmarks, is a new(ish) form of data activation: a way of turning domain data into something models can be measured against, ranked by, and event…

i am still pretty bad at collecting things i read. the attempts are worth it though, i think. mostly because the act of collecting pushes a little against the default “decay” (i.e., where links disappear into saved tabs, impressions flatten out, and then a

a nature medicine paper has been showing up in my feed recently: the one claiming general-purpose llms beat specialized clinical tools (openevidence, uptodate) on medical benchmarks.1 i am having a hard time letting it go, so i want to write down why, as…

i read two agent papers a few weeks back, planning to write about both. by now one of them feels like a footnote while the other is the one i actually kept using. the one that survived is PEEK.

my screen has looked the same for a few weeks now. on the left, codex (sometimes claude) in a main pane where i’m reading through a plan, asking why it picked this decomposition, sketching an html walkthrough of what the change would touch. on the right, a

medmarks v1.0 dropped last week from the medARC group and got real attention, deservedly. it’s the largest fully open medical LLM eval suite to date: 30 benchmarks across a verifiable subset (Medmarks-V) and an open-ended LLM-as-a-judge subset (Medmarks-O…

a quick one. small adjustments to how i work with agents, none of them deep on their own. but i can feel them adding up, the workflow shifting in a way that feels worth pausing on before any of it stops feeling new. that’s mostly why i’m writing this. the…

a paper from Brodeur et al. (2026) has been making the rounds the past few days.1 the framing it’s traveling with is “OpenAI’s o1 correctly diagnosed 78.3% of cases in NEJM clinicopathologic conferences, outperforming human physicians.” it didn’t click for

a week ago i wrote about a memory MCP i was using as a second brain. a few notes from week two. most of my actual work this week went into an evaluation framework i’m building, and the memory system was on for all of it (and for the rest of what was going…

i’ve been running a memory MCP as a “second brain” for the past week. a few notes, since the angle feels worth writing about even if i can’t tell yet whether it actually works. most of my work happens across a few different surfaces: Claude Code in the te…

Borges has a very short story about an empire whose cartographers kept producing larger and larger maps, until they built one the size of the empire itself.1 the following generations, less enchanted, saw it was useless and abandoned it to the weather. ma…

so this post is comprised of a few thoughts that converged into a tool. first: building small things is the new procrastination. i acknowledge that fully. and yet i keep finding myself building small solutions for specific usecases, and i think it comes d…

For various reasons1, i found myself away from ‘work work’ for the past couple of weeks, and also mostly away from a laptop2, and because of that, first of all i feel rusty and out of touch with the research areas (and some aspects of agentic coding). we’…

I needed a way to make diagrams for posts and papers.

I’ve been noticing something about how I work with Claude.

A friend who drives a lot asked if there was an audio version of my posts.

Opus 4.6 came out ~20 hours ago and I wanted to get a feel for it.

How can someone who enjoys thinking — enjoys the cognitive load — use coding agents and LLMs to foster continued learning, and not skill degradation?

In the last couple of months we’ve been working on a health agent.

“The Entertainment is real, and it’s called Instagram Reels.” — Will Gottsegen, The Atlantic Not a unique observation (the connection is clear).

A foundation model I’ve been working on recently got published in Nature.1 For a while I’ve wanted to write this.

The landscape is shifting in recent years — it’s a cliche to start texts like this these days, but the fact that it’s a cliche doesn’t make it any less true.1 In 2019, the folks at Andreessen Horowitz wrote this about data (in a piece titled The Empty Pro…

For a while now I’ve been collecting too many things to read and think about, mostly in twitter ‘saved links’.