SWE budgets: from Opex to Capex
Jay Hack · Jul 2026
The increasing autonomy of code agents has fundamentally changed what is possible in software engineering.
writing
Essays and notes.
Brain²: The Coming Wave
ClickUp · Jun 2026
Announcing ClickUp Brain² as the culmination of the Codegen acquisition: a new agent harness for general-purpose knowledge work agents, powered by frontier models, tools, memory, compute, automations, and ClickUp's work graph.
Ultracoding: the next frontier
Jay Hack · Jun 2026
On ultracoding: letting agents write code that spawns other agents, why code is the first domain to feel it (cheap bulk verification), how the bitter lesson pushes us toward runtime-defined multi-agent harnesses and agent-authored oversight UIs, and how the same pattern generalizes to large-scale knowledge work.
LLMs are not the Black Box you were promised
Jay Hack · Mar 2026
An adaptation of a thread on Anthropic's "On the Biology of a Large Language Model." It walks through how mechanistic interpretability and circuit tracing let us decompose a model's activations into human-interpretable features, watch genuine multi-step reasoning unfold (Dallas → Texas → Austin), and uncover quirks like Claude's non-human integer-addition algorithm — arguing that LLMs are far less of a black box than we were promised.
Act via Code
Graph-sitter / Codegen · Aug 2025
An essay arguing that the next step for software agents is not just better intelligence, but a more expressive action space: writing and executing programs against well-designed APIs. It connects lessons from Voyager's Minecraft agent to large-scale software engineering, explains why code execution enables composable and reviewable actions, and introduces graph-sitter as an open-source foundation for programmatic codebase manipulation.
SWE Agents are Better with Codemods
Graph-sitter / Codegen · Aug 2025
A practical case study showing how autonomous software agents can take on platform-level codebase changes when they operate through codemods. The post uses a Devin dead-code-removal task to show how agents can write, debug, run, and iterate on deterministic transformation programs that are easier to inspect than hundreds of individual AI-generated edits.
Adaptive Personalization for Beauty Retail
MIRA BEAUTY on Medium · Apr 2021
A commerce-focused exploration of adaptive personalization across the online shopping journey. The article frames e-commerce as a sequence of customer touchpoints, then describes how machine learning can select relevant content, product imagery, recommendations, and offers to help shoppers make better purchase decisions and improve long-term customer value.
Deep Learning for Cosmetics
MIRA BEAUTY on Medium · Jan 2018
A technical walkthrough of using computer vision to make shopping experiences more relevant to each customer. The post explains how face and eye embeddings, geometric normalization, triplet loss, and transfer learning can match shoppers with more useful product inspiration and buying guidance while filtering out superficial visual noise like lighting, pose, and styling.
in Pixels
Personal archive · Sep 2009 – Jan 2010
A personal archive of Jay's student-exchange blog from Nagano, Japan, spanning 26 posts from September 2009 through January 2010. The collection captures travel, language, school, culture, friendship, and coming-of-age observations from a much earlier era of personal writing.