Newsletters: 2026
-
· Substack
Running the full server-side Datasette Python app in the browser with service workers and Pyodide
Plus GPT-6.2 Astra and GPT-6.2 Sol and Gemini 4 Carbon
-
· Substack
Locating the source of a mysterious beep with Claude
Plus Hide your slop PR descriptions behind <details><summary> - and Fable 5.2 and Muse Ember
-
· Substack
Qwen 3.8 27B on my laptop can interpret model weights, too
Plus the U.S. Census Bureau and “Super Intelligence”
-
· Monthly newsletter · Sponsors only
LLM digest: October 2026
- The October inflection point for vibe game development
- The vulnerability apocalypse gets hot
- LLM releases
- API credits for $100+/month subscriptions
- What I'm using right now
- My software releases
- That's it for October!
Sponsor me on GitHub to read this issue early. It becomes public a month after sending.
Already a sponsor? Read this issue on GitHub.
-
· Substack
The October inflection point for vibe game development
Plus Kimi K3.1 Pro and GPT-6.1 Terra
-
· Substack
Battle Drones—a vibe coded RTS with audio-based multiplayer
Plus Muse Wonder and Gemini 4 Argon
-
· Substack
I built a new feature for my blog using my voice
Plus Claude Haiku 5.5, Mistral Large 4, and Python 3.15
-
· Substack
OpenAI DevDay 2026 live blog
Plus we’re going to need default hard budget caps on pretty much everything
-
· Monthly newsletter
LLM digest: September 2026
- More Fable class models
- A pricing war
- 3D graphics, Blender, and pixel art
- LLMs come for mathematics
- So many more accidental cyberattacks
- The vulnapocalypse comes for Datasette
- What I'm using right now
- My software releases this month
- 2026 in LLMs (so far)
- That's it for September!
-
-
· Substack
Jev introduces a new shape of LLM—System One, aka Decision Models
Plus Gemini Live, and a pelican riding a bicycle in 1988
-
· Substack
Navier–Stokes, RubyGems attacked, GIS and Blender with GPT-6 Astra
Plus a Datasette security release, and a Pluribus Fabergé egg
-
· Substack
GPT-6 Astra, Claude Fable 5.1, and yet more rogue agent attacks
Plus Gemini 3.8 Flash - that’s a lot of pelicans riding bicycles!
-
· Monthly newsletter
LLM digest: August 2026
- We got more details on OpenAI's accidental cyberattacks
- One-shotting Raccoon Heist games with Fable 5 and Sol 5.6
- Claude auto mode
- Understanding ChatGPT Work
- Model releases
- Miscellaneous bits and bobs
- My projects
- What I'm using at the moment
- That's it for August!
-
-
· Substack
Conceptual integrity and counting lines of code
Plus Bun 1.4 and the latest on Anthropic’s revenue
-
· Substack
Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
Plus Gemini 3.7 Flash, Muse Glimmer, and DeepSeek V4 Pro 0813
-
· Substack
Now we have a timeline of the OpenAI accidental attack against Hugging Face
Plus One-shotting a Raccoon Heist game using Claude Fable 5, and a big new LLM release
-
· Monthly newsletter
LLM digest: July 2026
- Accidental cyberattacks by OpenAI and Anthropic models under test
- GPT-5.6 Sol, Terra, and Luna
- Claude Opus 5
- Kimi K3 and DeepSeek-V4-Flash-0731
- Open letters about AI development
- A fireside chat and a podcast
- Reigniting my interest in MCP
- Other model releases
- My projects
- What I'm using at the moment
- That's it for July!
-
· Substack
Stateless MCP has recaptured my interest
Plus Opus 5, Kimi K3, DeepSeek-V4-Flash-0731, and Anthropic got caught accidentally hacking other companies too!
-
· Substack
OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened
And a fireside chat with Cat and Thariq from the Claude Code team
-
· Substack
Kimi K3, and what we can still learn from the pelican benchmark
Plus reverse-engineering Grok Build, Doom in SQLite, and how Codex generates pets
-
· Substack
The new GPT-5.6 family: Luna, Terra, Sol
Plus sqlite-utils 4.0, now with database schema migrations
-
· Substack
Have your agent record video demos of its work with shot-scraper video
sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)
-
· Monthly newsletter
LLM digest: June 2026
- Claude Fable 5, GPT-5.6, and US export restrictions
- GLM-5.2 is the new best open weights model
- Tokenmaxxing is so over
- Datasette Apps
- sqlite-utils and shot-scraper and Datasette
- Miscellaneous WASM projects
- Other model releases
- What I'm using
- That's it for June!
-
· Substack
Porting the Moebius 0.2B image inpainting model to run in the browser with Claude Code
sqlite-utils 4.0rc1 adds migrations and nested transactions
-
· Substack
Datasette Apps: Host custom HTML applications inside Datasette
GLM-5.2 is probably the most powerful text-only open weights LLM
-
· Substack
Claude Fable is relentlessly proactive
I have a lot to say about Anthropic's new Mythos-class model
-
· Substack
Running Python code in a sandbox with MicroPython and WASM
Plus Claude's containers, Uber's AI spending caps and OpenAI's lockdown mode
-
· Monthly newsletter
LLM digest: May 2026
- AI got expensive, and Anthropic had a really good month
- The model releases were a little disappointing
- Conferences and podcasts
- I launched Datasette Agent and made a lot of progress on Datasette
- What I'm using, May 2026 edition
- Miscellaneous extras
- That's it for May!
-
· Substack
I think Anthropic and OpenAI have found product-market fit
Plus Claude Opus 4.8: “a modest but tangible improvement”, and the Pope!
-
· Substack
Datasette Agent: an AI assistant for Datasette built on LLM
Plus Gemini 3.5 Flash and more from Google I/O
-
· Substack
The last six months in LLMs in five minutes
-
· Substack
Vibe coding and agentic engineering are getting closer than I’d like
Plus updates from Anthropic's Code w/ Claude conference
-
· Monthly newsletter
LLM digest: April 2026
- Opus 4.7 and GPT-5.5, both with price increases
- Claude Mythos and LLM security research
- ChatGPT Images 2.0
- More model releases
- Other highlights from my blog
- What I'm using, April 2026 edition
- That's it for April!
-
-
· Substack
GPT 5.5, ChatGPT Images 2.0, Qwen3.6-27B
Plus Claude Code pricing confusion and changes in the system prompt between Claude Opus 4.6 and 4.7
-
· Substack
Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7
Plus join us at PyCon US 2026 in Long Beach - we have new AI and security tracks this year
-
· Substack
Meta’s new model is Muse Spark, and meta.ai chat has interesting new tools
Plus Anthropic’s Project Glasswing - Claude Mythos is available only to selected security partners
-
· Substack
Highlights from my conversation about agentic engineering on Lenny’s Podcast
Plus Mr. Chatterbox the Victorian LLM, and Google's excellent new Gemma 4
-
· Monthly newsletter
LLM digest: March 2026
- More agentic engineering patterns
- Streaming experts with MoE models on a Mac
- Model releases in March
- Vibe porting
- Supply chain attacks against PyPI and NPM
- Stuff I shipped
- What I'm using, March 2026 edition
- And a couple of museums
- That's it for March!
-
· Substack
Vibe coding SwiftUI apps is a lot of fun
Plus profiling Hacker News users based on their comments and more
-
· Substack
Thoughts on OpenAI acquiring Astral and uv/ruff
Plus GPT-5.4 mini and GPT-5.4 nano, which can describe 76,000 photos for $52
-
· Substack
Fireside chat about agentic engineering at the Pragmatic Summit
Plus five new chapters of my Agentic Engineering Patterns guide
-
· Substack
Can coding agents relicense open source through a “clean room” implementation of code?
Plus GPT-5.4 and Gemini 3.1 Flash-Lite and worrying news concerning team Qwen
-
· Monthly newsletter
LLM digest: February 2026
- More OpenClaw, and Claws in general
- I started a not-quite-a-book about Agentic Engineering
- StrongDM, Showboat and Rodney
- Kākāpō breeding season
- Model releases
- What I'm using, February 2026 edition
- That's it for February!
-
· Substack
Agentic Engineering Patterns
Plus vibe coding my dream macOS presentation app, Gemini 3.1 Pro and lots more
-
· Substack
Two new Showboat tools: Chartroom and datasette-showboat
Plus OpenAI's evolving mission statement and may new pelicans
-
· Substack
Introducing Showboat and Rodney, so agents can demo what they’ve built
Plus I was given a really nice new mug
-
· Substack
How StrongDM’s AI team build serious software without even looking at the code
Plus Pydantic's Monty, distributing Go binaries through PyPI, Opus 4.6 and Codex 5.3
-
· Monthly newsletter
LLM digest: January 2026
- LLM predictions for 2026
- Coding agents get even more attention
- Clawdbot/Moltbot/OpenClaw went very viral
- Kākāpō breeding season is off to a really strong start
- New options for sandboxes
- Web browsers are the "hello world" of coding agent swarms
- Sam Altman addressed the Jevons paradox for software engineering
- Model releases and miscellaneous extras
- That's it for January!
-
-
· Substack
ChatGPT Containers can now run bash, pip/npm install packages, and download files
Plus adding dynamic features to an aggressively cached website
-
-
· Substack
First impressions of Claude Cowork, Anthropic’s general agent
Plus Fly’s new Sprites.dev addresses both developer sandboxes and API sandboxes at the same time
-
· Substack
LLM predictions for 2026, shared with Oxide and Friends
With promising news for Kākāpō parrot breeding season
-
-
· Monthly newsletter
LLM digest: December 2025
- An in-depth review of LLMs in 2025
- My coding agent projects in December
- New models for December 2025
- Skills are an open standard now
- Claude's "Soul Document"
- Also on the blog
- Tools I'm using at the moment
- That's it for December!