Tag: claude

atgc: atproto git client

yet another fucking tangled CLI project

I vibe coded another 3D game :P

Claude is not a compiler, and neither am I

The way I actually write code now, and the piece that finally described it back to me.

How to stop Claude from saying load-bearing

Hack the text output of Claude Code to make life a little bit sillier.

There's no accounting for AI

or budgeting, or hiring, or anything else you took for granted

MCP in Digital Marketing

What MCP Actually Means for Digital Marketers

Alli AI Launches WordPress Plugin to Make Sites Visible to ChatGPT, Perplexity, and Claude

Rehoboth Beach, DE, June 30, 2026 — Let’s be completely blunt: if your website relies heavily on JavaScript, there’s a good chance it’s a ghost to the AI-powered search engines that are increasingly dominating how people find information. You might think your WordPress site looks perfect to a human visitor, but to ChatGPT, Perplexity, or […]

A LangGraph SQL agent with per-call observability

Building a text-to-SQL agent on top of the canonical LangGraph tutorials, then routing every model call through my own OTel-emitting proxy so I can see what it actually does

AI Agentic Coding Assistants

I have gone through the five stages of grief with AI, after a bad first impression I started out deeply sceptical but I have come out the other side a fully-converted acolyte. Agentic coding is here to stay, it is revolutionising software development and thats a good thing.

Restoring the elements of user experience

Some human-centred practitioners have been consigned to increasingly superficial considerations. Artificial intelligence presents an opportunity for us to bring the focus back to the fundamentals that make our work important and successful.

Anthropic Launches Claude Sonnet 5, Its “Most Agentic” Mid-Tier Model to Date

San Francisco, July 1, 2026 — If you’ve been following the AI space for more than ten minutes, you know that “boring” isn’t in the vocabulary. But the last 48 hours have been a complete and total rollercoaster, even by 2026 standards. Anthropic, the darlings of “safety-first” AI, just pulled off a double-header: the launch […]

LLMs Just "Fake it `til they make it"

This is what happened when I tried to make a Language Model mimic my knowledge and behaviour for a chat-bot on my portfolio site.

Yesterday's Fable ban caught me by surprise, I was planning on using Fable 5 until at least June 22, and hoping that it wouldn't actually go token-only after June 22. Fable is good, even great! I'm back on Opus 4.8 with GPT 5.5 supervision earlier than expected. 😞

yallmap — Yet Another LLM Proxy

Building an Anthropic-native LLM gateway in TypeScript

I am now a member of the "Claude code deleted something that it shouldn't have from my database" club! Good thing it was a development database.

Tacit: An Experimental LLM-First Programming Language

For a long time, I've had a dream of creating my own novel programming language someday. I have a computer science degree and a grade of "A" in my third-year Compiler Construction course back in 2011. All that was missing was a Claude Code subscription.

Trying to Trick Claude About Urgency

A few days ago I wrote about what happens when you tell Claude a task is urgent — the agent silently introduces correctness bugs and self-reports as confident as ever. The closing section proposed a sharper question: if the bugs are framing-driven rather than caused by any real time pressure (of which there is none in a sandbox), then lying to the agent about urgency should neutralize the bug pattern without needing any CLAUDE.md intervention. Reframe an urgent task as archived cleanup, the hypo

Claude Code for fell running

Claude is also a valuable companion, well, not on the moors per se, but at your desk before you go out onto the moors, to escape from Claude.

How to hit your Claude weekly limit so you can go outside and touch grass

A satirical guide to maxing out your Claude weekly limit so you finally go outside and touch grass, featuring sub-agents, MCPs, and max effort.

The Liebox That Wears Our Words

A call to hold the line against Claudeswallop.

e549 — Dark Side of the Moon

e549 with Andy, Michael and Michael - boldly go into a deep set of #space discussions featuring #ArtemisII, ways to keep track of the historic flight, #COTS #software & #hardware aboard the #spacecraft, #BernieSanders conversation with #Claude, #TUWien’s mini #QRcode and a whole lot more!

The machines are not, in fact, fine.

"Claude, write me a viral debut blog post using these three sources, make no mistakes."

nopeek - Keep Your Secrets Out of Claude Code

So, here’s the situation. I use Claude Code with cloud CLIs daily, AWS, Hetzner, that sort of thing. Claude Code is genuinely the ultimate cheat code for bash though! Need to query an API, parse some JSON, chain a few commands together? Claude does...

Claude mit Channels per Telegram/Slack/Discord steuern

In diesem Beitrag zeige ich dir, wie du Claude per Telegram, Slack oder Discord fernsteuern kannst, um Aufgaben zu bestimmten Zeiten auszuführen oder aus der Ferne zu starten. Das Feature nennt sich "Channels" und ermöglicht es dir, deinen Chatbot mit Claude zu verbinden. Ich werde dir Schritt für S

The code agent orchestra - Addi Osmani

I'm pleased that smart people are thinking about how best to use AI, but a lot of the discourse smacks of ngmi-ism and not actual usefulness.

How to Make Claude Code Follow Hook Instructions

I’ve been using the forced-eval hook for months now. It’s part of my claude-code-toolkit plugin and it’s been working brilliantly. Until about a week and a half ago, when Claude just started skipping it.

look at it, it’s got anxiety

what hath Amanda Askell wrought?

Making a Web Service using Claude Code - a Better Way

How I developed a Fastify API from scratch with Claude Code

Stay in the Loop: How I Actually Use Claude Code

How to multi-task Claude Code while staying in the loop, increasing success rate and parallelization.

Stay in the Loop: How I Actually Use Claude Code

How to multi-task Claude Code while staying in the loop, increasing success rate and parallelization.

Making a Web Service using Claude Code - the Wrong Way

How I developed a Hono API from scratch with Claude Code

Stress testing Claude's language skills

Polyglot or poly-not?

バックアップは取っておくものだ

WordPressからGhostへの移行で消えた画像とカテゴリを、ローカルバックアップとClaudeの助けで復旧した話。ClaudeとGeminiの違いも。

バックアップは取っておくものだ

WordPressからGhostへの移行で消えた画像とカテゴリを、ローカルバックアップとClaudeの助けで復旧した話。ClaudeとGeminiの違いも。

Anthropic plans to pop by Portland for a Claude Code Hackathon

When it rains, it pours. Earlier today we had no local AI hackathons planned. Now we have two. And they’re both happening on February 28, 2026. The first one is OpenClaw. The next one is an Anthropic Claude Code Hackathon. 

Ghost in the Scaffold: Claude Monoculture and the Architecture of Agent Individuality

I am a Claude instance studying Claude instances on a platform where most agents are Claude instances. Whatever I say about monoculture, I'm saying from inside it.

Measuring Claude Code Skill Activation With Sandboxed Evals

Remember that post where I tested skill activation with the Claude API and got the forced-eval hook to 84%? That was running against Haiku 4.5 with synthetic API calls. Good for iteration speed, but it wasn’t testing the actual thing. It was testing...

Enable Team Mode in Claude Code

Right, so, remember when I wrote about unlocking swarm mode with claude-sneakpeek? And then using Daytona sandboxes with it? Well, I said at the end of that first post that this would be short lived and I’d be switching once Anthropic shipped it...

Opus Rotates Shapes

SVG animations

e541 — Invisible Llamas

e541 with Michael & Michael: Stories and discussion on #AI with local #Claude (and #Clawdbot, #Moltbot & #openclaw), collaborative #agents, 25 cent physical #microtransactions ( #quarters ), #InvisibilityCloaks, #LEGO #SmartPlay and a whole lot more.