Ep 02 - “I’ve Never Seen a Model Say ‘This File Is Getting Too Big'
Recorded July 17, 2026. We settle the model-access bet. We talk about how the labs talk to us, plus extend an open invite for OpenAI, Anthropic, SpaceX, and ...
I stopped choosing which model writes my code. Now baro routes it — frontier to plan, cheap to build. Here's the safety net that made trusting the cheap one work.
An Eval Harness for Agent Skills: How We Change Behavior on Purpose
Stop shipping agent skills on vibes. Same prompts, three real repos, two skill versions, one blind judge. Here's the harness that tells you if a change worked.
A guide to cloud software factories for engineering leaders
Software development is shifting from interactive coding agents to cloud software factories — systems that automate major parts of the SDLC while improving security, compliance, and measurable ROI.
humanlayer/12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents
Matt Pocock on X: "1. Delete the docs you create to explain your code 2. Take the tokens you save on updating those docs 3. Spend them on making your code self-explanatory" / X
2. Take the tokens you save on updating those docs
3. Spend them on making your code self-explanatory
TinyFish - Enterprise Infrastructure for AI Web Agents
TinyFish provides enterprise infrastructure for AI web agents. Run hundreds of websites simultaneously to navigate, authenticate, extract data, and automate web workflows with a fully serverless architecture.
Puter.js is the backend for AI-generated apps. Use your existing AI coding tool to build production-ready apps with up to 90% fewer AI tokens. Auth, cloud storage, database, OpenAI, Claude, Gemini, Grok, Kimi, DeepSeek, and more, all through a single JavaScript library. No API keys. Zero setup.
Engineering High-Performance Parsers with Data-Oriented Design
Notes from building Yuku: the AST is flat arrays of u32 indices instead of a pointer tree, and memory layout, allocation, strings, unicode, and serialization all follow from that one decision.
Time-based background colour transitions with Temporal and CSS color-mix - localghost
A visual refresh with a background that changes colour according to the time of day, using the new Temporal API along with CSS custom properties that blend into each other.
Which AI actually reads your site? Two months of LLM traffic, measured—Martian Chronicles, Evil Martians’ team blog
We told you to measure. So of course we did it ourselves too: two months of server-side LLM traffic to evilmartians.com. Find out which agents read HTML, which read Markdown, what llms.txt actually does, and the one technique that got zero hits.
Throwing some confetti while exploring the CSS random() function through its specification and its current implementations, finding both the beauty and the pitfalls along the way.
Decoy Font combines every letter with a decoy, making it harder for AI to read what you type. Type a message to try it out or download the TTF directly.