Live blog: Code w/ Claude 2026
Live blog: Code w/ Claude 2026
I'm at Anthropic's Code w/ Claude event today. Here's my live blog of the morning keynote sessions. Tags: ai, generative-ai, llms, anthropic, claude, claude-code, live-blog
Lire
Vibe coding and agentic engineering are getting closer than I'd like
Vibe coding and agentic engineering are getting closer than I'd like
I recently talked with Joseph Ruscio about AI coding tools for Heavybit's High Leverage podcast: Ep. #9, The AI Coding Paradigm Shift with Simon Willison. Here are some of my highlights, including my disturbing realization that vibe coding and agentic engineering have started to converge in my own work. One thing I really enjoy about podcasts is that they sometimes push me to think out loud in a way that exposes an idea I've not previously been able to put into words. Vibe coding and agentic…
Lire
Eating My Own Dog Food: How I Used the Framework to Write the Post About the Framework
In “Don’t Automate Your Moat,” I argue that engineering organizations should match AI autonomy to two independent dimensions: business risk and competitive differentiation. I used AI Gateway cost controls as a worked example throughout the piece because a single feature touches all four quadrants depending on which piece you’re building. A piece making that argument […]
Lire
The Organization Is the Bottleneck
The Organization Is the Bottleneck
Everyone is adopting AI coding tools. Engineers are writing code faster than ever. But are organizations actually delivering value faster? That’s not obvious. I wrote Enabling Microservice Success with a big focus on engineering enablement, guardrails, automated testing, active ownership, and light touch governance. I didn’t know AI coding agents were coming, but it turns […]
Lire
datasette-referrer-policy 0.1
datasette-referrer-policy 0.1
Release: datasette-referrer-policy 0.1 The OpenStreetMap tiles on the Datasette global-power-plants demo weren't displaying correctly. This turned out to be caused by two bugs. The first is that the CAPTCHA I added to that site a few weeks ago was triggering for the .json fetch requests used by the map plugin, and since those weren't HTML the user was not being asked to solve them. Here's the fix. The second was that OpenStreetMap quite reasonably block tile requests from sites that use a…
Lire
Our AI started a cafe in Stockholm
Our AI started a cafe in Stockholm
Our AI started a cafe in Stockholm Andon Labs previously started an AI-run retail store in San Francisco. Now they're running a similar experiment in Stockholm, Sweden, only this time it's a cafe. These experiments are interesting, and often throw out amusing anecdotes: During the first week of inventory, Mona ordered 120 eggs even though the café has no stove. When the staff told her they couldn’t cook them, she suggested using the high-speed oven, until they pointed out the eggs would likely…
Lire
Train Classical ML Models on Large Datasets
Extend the Bagging objective to any ML algorithm.
Lire
What matters (or should matter), at the Musk-OpenAI trial
Two perspectives on what’s transpired so far
Lire
The AI Ad-Hoc Prior Restraint Era Begins
The White House has ordered Anthropic not to expand access to Mythos, and is at least seriously considering a complete about-face of American Frontier AI policy into a full prior restraint regime, where anyone wishing to release a highly capable new model will have to ask for permission
Lire
Breaking: Autonomous Agents are a Shitshow
Sorry to use a technical term in the title
Lire
datasette-llm 0.1a7
datasette-llm 0.1a7
Release: datasette-llm 0.1a7 Mechanism for configuring default options for specific models. Part of Datasette's evolving support mechanism for plugins that use LLMs. It's now possible to configure a model with default options, e.g. to say all enrichment operations should use a specific model with temperature set to 0.5. Tags: llm, datasette
Lire
llm-echo 0.5a0
llm-echo 0.5a0
Release: llm-echo 0.5a0 New -o thinking 1 option to help test against LLM 0.32a0 and higher. This plugin provides a fake model called "echo" for LLM which doesn't run an LLM at all - it's useful for writing automated tests. You can now do this: uvx --with llm==0.32a1 --with llm-echo==0.5a0 llm -m echo hi -o thinking 1 This will fake a reasoning block to standard error before returning JSON echoing the prompt. Tags: llm
Lire
Quoting John Gruber
Quoting John Gruber
So it’s well known that Y Combinator owns some stake in OpenAI. But how big is that stake? This seems like devilishly difficult information to obtain. I asked around and a little birdie who knows several OpenAI investors came back with an answer: Y Combinator owns about 0.6 percent of OpenAI. At OpenAI’s current $852 billion valuation, that’s worth over $5 billion. — John Gruber, Y Combinator’s Stake in OpenAI Tags: openai, y-combinator, ai, john-gruber
Lire
Granite 4.1 3B SVG Pelican Gallery
Granite 4.1 3B SVG Pelican Gallery
Granite 4.1 3B SVG Pelican Gallery IBM released their Granite 4.1 family of LLMs a few days ago. They're Apache 2.0 licensed and come in 3B, 8B and 30B sizes. Granite 4.1 LLMs: How They’re Built by Granite team member Yousaf Shah describes the training process in detail. Unsloth released the unsloth/granite-4.1-3b-GGUF collection of GGUF encoded quantized variants of the 3B model - 21 different model files ranging in size from 1.2GB to 6.34GB. All 21 of those Unsloth files add up to 51.3GB,…
Lire