Quitting programming as a career right now because of LLMs would be like quitting carpentry as a career thanks to the invention of the table saw.

Tags: careers, ai-assisted-programming, generative-ai, ai, llms

On two occasions I have been asked, — "Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out ?" In one case a member of the Upper, and in the other a member of the Lower, House put this question. I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question.

— Charles Babbage, Passages from the Life of a Philosopher, 1864

Tags: charles-babbage

Mandelbrot in x86 assembly by Claude Inspired by a tweet asking if Claude knew x86 assembly, I decided to run a bit of an experiment. I prompted Claude Sonnet 4: Write me an ascii art mandelbrot fractal generator in x86 assembly And got back code that looked... like assemb...

TIL: Using Playwright MCP with Claude Code Inspired by Armin ("I personally use only one MCP - I only use Playwright") I decided to figure out how to use the official Playwright MCP server with Claude Code. It turns out it's easy: claude mcp add playwright npx '@playwright/m...

One of the best examples of LLM developer tooling I've heard is from a team that supports software from the 80s-90s. Their only source of documentation is video interviews with retired employees. So they feed them into transcription software and get summarized searchable notes out the other end.

— Kevin Webb, a couple million lines of Smalltalk

Tags: small, ai-assisted-programming, ai, llms

Sometimes a service with a free plan will decide to stop supporting it. I understand why this happens, but I'm often disappointed at the treatment of existing user's data. It's easy to imagine users forgetting about their old accounts, missing the relevant emails and then discovering too late that their data is gone.

Inspired by today's news about PlanetScale PostgreSQL I signed into PlanetScale and found I had a long-forgotten trial account there with a three-year-old database on their free tier. That free tier was retired in March 2024.

Here's the screen that greeted me in their control panel:

What a great way to handle retiring a free plan! My data is still there, and I have the option to spin up a database for 24 hours to help get it back out again.

Tags: saas, databases

Using LLMs for code archaeology is pretty fun. I stumbled across this blog entry from 2003 today, in which I had gotten briefly excited about ColdFusion and implemented an experimental PHP template engine that used XML tags to achieve a similar effect: <h1>%title%</...

Announcing PlanetScale for Postgres PlanetScale formed in 2018 to build a commercial offering on top of the Vitess MySQL sharding open source project, which originated at YouTube. The founders were the co-creators and maintainers of Vitess. Today they're announcing a private...

To misuse a woodworking metaphor, I think we’re experiencing a shift from hand tools to power tools.

You still need someone who understands the basics to get the good results out of the tools, but they’re not chiseling fine furniture by hand anymore, they’re throwing heaps of wood through the tablesaw instead. More productive, but more likely to lose a finger if you’re not careful.

— mrmincent, Hacker News comment on Claude Code

Tags: ai-assisted-programming, claude-code, hacker-news, generative-ai, ai, llms

Using Claude Code to build a GitHub Actions workflow

I wanted to add a small feature to one of my GitHub repos - an automatically updated README index listing other files in the repo - so I decided to use Descript to record my process using Claude Code. Here's a 7 minute video showing what I did.

I've been wanting to start producing more video content for a while - this felt like a good low-stakes opportunity to put in some reps.

Tags: screencast, youtube, ai, github-actions, llms, ai-assisted-programming, anthropic, claude, coding-agents, claude-code

I just sent out the second edition of my sponsors only monthly newsletter. Anyone who sponsors me for $10/month or more on GitHub gets this carefully hand-curated summary of the last month in AI/LLMs/my projects designed to be readable in ten minutes or less.

My regular newsletter remains free - the monthly one is the only paywalled content I produce, the idea being that you can pay me to send you less.

Here's the first edition for May 2025 as a preview of what you can expect. You'll get access to the June digest and the full archive automatically if you decide to start sponsoring.

Tags: newsletter

microsoft/vscode-copilot-chat As promised at Build 2025 in May, Microsoft have released the GitHub Copilot Chat client for VS Code under an open source (MIT) license. So far this is just the extension that provides the chat component of Copilot, but the launch announcement p...

llvm: InstCombine: improve optimizations for ceiling division with no overflow - a PR by Alex Gaynor and Claude Code Alex Gaynor maintains rust-asn1, and recently spotted a missing LLVM compiler optimization while hacking on it, with the assistance of Claude (Alex works for ...

Agentic Coding: The Future of Software Development with Agents Armin Ronacher delivers a 37 minute YouTube talk describing his adventures so far with Claude Code and agentic coding methods. A friend called Claude Code catnip for programmers and it really feels like this. I ...

How to Fix Your Context Drew Breunig has been publishing some very detailed notes on context engineering recently. In How Long Contexts Fail he described four common patterns for context rot, which he summarizes like so: Context Poisoning: When a hallucination or other er...

Tip: Use keyword-only arguments in Python dataclasses

Useful tip from Christian Hammond: if you create a Python dataclass using @dataclass(kw_only=True) its constructor will require keyword arguments, making it easier to add additional properties in the future, including in subclasses, without risking breaking existing code.

Via @chipx86.bsky.social

Tags: python

Continuous AI GitHub Next have coined the term "Continuous AI" to describe "all uses of automated AI to support software collaboration on any platform". It's intended as an echo of Continuous Integration and Continuous Deployment: We've chosen the term "Continuous AI” to al...

The term context engineering has recently started to gain traction as a better alternative to prompt engineering. I like it. I think this one may have sticking power. Here's an example tweet from Shopify CEO Tobi Lutke: I really like the term “context engineering” over prom...

Project Vend: Can Claude run a small shop? (And why does that matter?) In "what could possibly go wrong?" news, Anthropic and Andon Labs wired Claude 3.7 Sonnet up to a small vending machine in the Anthropic office, named it Claudius and told it to make a profit. The system ...

Introducing Gemma 3n: The developer guide Extremely consequential new open weights model release from Google today: Multimodal by design: Gemma 3n natively supports image, audio, video, and text inputs and text outputs. Optimized for on-device: Engineered with a focus o...

Yesterday Anthropic got a bunch of buzz out of their new window.claude.complete() API which allows Claude Artifacts to run their own API calls. It turns out Gemini had beaten them to that feature by over a month, but the announcement was tucked away in a bullet point of thei...

Two interesting new products for running code in a sandbox today. Cloudflare launched their Containers product in open beta, and added a new Sandbox library for Cloudflare Workers that can run commands in a "secure, container-based environment": import { getSandbox } from "@...

Build and share AI-powered apps with Claude Anthropic have added one of the most important missing features to Claude Artifacts: apps built as artifacts now have the ability to run their own prompts against Claude via a new API. Claude Artifacts are web apps that run in a st...

Creating art is a nonlinear process. I start with a rough goal. But then I head into dead ends and get lost or stuck.

The secret to my process is to be on high alert in this deep jungle for unexpected twists and turns, because this is where a new idea is born.

I can't make art when I'm excluded from the most crucial moments.

— Christoph Niemann, An Illustrator Confronts His Fears About A.I. Art

Tags: art, ai, generative-ai

Gemini CLI First there was Claude Code in February, then OpenAI Codex (CLI) in April, and now Gemini CLI in June. All three of the largest AI labs now have their own version of what I am calling a "terminal agent" - a CLI tool that can read and write files and execute comman...

Anthropic wins a major fair use victory for AI — but it’s still in trouble for stealing books Major USA legal news for the AI industry today. Judge William Alsup released a "summary judgement" (a legal decision that results in some parts of a case skipping a trial) in a laws...

I've added a Disclosures section to my about page, listing my various sources of income and the companies that directly sponsor my work or have supported it in the recent past.

I do not receive any compensation writing about specific topics on this blog - no sponsored content! I plan to continue this policy. If I ever change this I will disclose that both here and in the post itself. [...]

I see my credibility as one of my most valuable assets, so it's important to be transparent about how financial interests may influence my writing here.

I took inspiration from Molly White's disclosures page.

Tags: blogging, molly-white

Here's a fascinating new entrant into the AI-assisted-programming / coding-agents space by Fly.io, introduced on their blog in Phoenix.new – The Remote AI Runtime for Phoenix: describe an app in a prompt, get a full Phoenix application, backed by SQLite and running on Fly's ...

So you you can think really big thoughts and the leverage of having those big thoughts has just suddenly expanded enormously. I had this tweet two years ago where I said "90% of my skills just went to zero dollars and 10% of my skills just went up 1000x". And this is exactly what I'm talking about - having a vision, being able to set milestones towards that vision, keeping track of a design to maintain or control the levels of complexity as you go forward. Those are hugely leveraged skills now compared to knowing where to put the amperands and the stars and the brackets in Rust.

— Kent Beck, interview with Gergely Orosz

Tags: gergely-orosz, ai-assisted-programming, ai, careers

My First Open Source AI Generated Library Armin Ronacher had Claude and Claude Code do almost all of the work in building, testing, packaging and publishing a new Python library based on his design: It wrote ~1100 lines of code for the parser It wrote ~1000 lines of tests ...