A Swarm of Blood Robots — by Craig Mod
Using LLMs to find relatives, build software, and do annoying things you don't want to do
Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
Friday’s big release was Qwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba’s Qwen research lab. I’ve been looking forward to this one: 27B is an …
Chad Arimura | My agent setup
Personal website of Chad Arimura - My agent setup
cathrynlavery/diagram-design: 29 editorial diagram types for Claude Code. Self-contained HTML + SVG. No shadows, no Mermaid-slop.
Thirteen editorial diagram types for Claude Code. Self-contained HTML + SVG. No shadows, no Mermaid-slop. - cathrynlavery/diagram-design
I'm done using AI
Why I'm stopping using AI for coding (and anything else) after using it earnestly for a year and coming to understand the harms it causes on personal, societal, and environmental levels.
OpenChamber — Agentic Development Environment for AI Coding
A control room for AI coding across desktop, browser, phone, and VS Code. Watch agents work, review diffs, branch sessions, and keep the whole board visible.
If you haven’t recently used Claude Code*, you might not understand where AI is at
A report on a series of mini machine learning projects, executed with, and mostly by, Claude
Plato’s Warning Has Been Vindicated | THR Web Features | Web Features | The Hedgehog Review
We now believe that our newest tools, once perfected, will relieve us of the need to be informed at all.
Why You Should Almost Never Use AI to Write Anything Substantive
Texts on this and that.
Some thoughts about Anthropic’s new cryptanalysis results – A Few Thoughts on Cryptographic Engineering
Yesterday Anthropic published two new cryptanalysis results, both outputs of Claude Mythos, their (still) unreleased advanced model. The first of these results attacks a signature scheme called HAW…
Ninth Circuit: Your AI Agent Can’t Violate Hacking Law. But You Might. | Techdirt
The rise of AI is bringing a bunch of fascinating legal questions that are harder to answer than many expect. The latest one: who is liable if an agentic system running on its own hacks someone? Th…
i tried making a game with ai and then this happened
ALEX NO
Pi Can Finally Go Full YOLO Without Wrecking Production - YouTube
Massive thanks to Docker for supporting the channel and sponsoring ...
firecrawl/pdf-inspector: Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions. - firecrawl/pdf-inspector
The Shape of Things to Come, Part 1: The Continuous Thunderdome — Steve Yegge
Part 1: The Continuous Thunderdome. Loops and graphs, Wheelhouse and Beads, the end of human code review, the Land Rush that replaces CI/CD, and the Wish Factory — a field report from 12 months in the future.
trycompai/crm
An open-source, agentic-first CRM. A durable research agent is the product. The database is just where it writes things down.
Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp)
Tuesday was Stateless MCP day—the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant …
Hubble.md
The Session You Cannot Take With You | EARENDIL
Inference APIs are filling sessions with encrypted reasoning, hidden search results, opaque compaction, and encrypted subagent messages. A growing form of lock-in.
An announcement from Superlogical
Building the multiplexer for all work.
The End of an Era - Hugh Howey
We knew this day would come. Some of us have known for decades, have been writing and pontificating about this since Ken Jennings lost at Jeopardy and Kasparov lost at chess. The writing was on the wall, and now the writing is everywhere. Literally. Artificial Intelligence is writing about as well as humans — at […]
Amazon accidentally spent $1.8 million using Claude for menial coding task, went 860% over budget — 'catastrophically expensive' coding blunders discovered in internal Amazon AI usage metrics
A million dollar "whoopsie"
VladUZH/qwen-scribe: Private, local transcription and system-wide dictation for Apple Silicon.
Private, local transcription and system-wide dictation for Apple Silicon. - VladUZH/qwen-scribe
What just happened to TheNumbers.com should worry us all
If you work in or around the film industry, there is a decent chance you have used the work of The Numbers this month, whether you realise it or not.
OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model’s guardrail features turned off. Rather than solve the test, the …
Nativ — Local AI for your Mac
Frontier intelligence on your desk. No accounts, subscriptions, or cloud.
modem-dev/hunk: Review-first terminal diff viewer for agentic coders
Review-first terminal diff viewer for agentic coders - modem-dev/hunk
Moshi — SSH & MOSH Terminal for Claude Code & AI Agents
Mobile terminal app for AI coding agents. Connect to Claude Code, Codex, and other CLI tools from your iPhone or Android device.
Herdr: one terminal for the whole herd
Terminal-native agent runtime and multiplexer. Detach, reattach, SSH in, and keep every agent visible.
Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal Help? - Charles AZAM
I gave Claude Fable 5 and GPT-5.6 Sol the same unpublished NP-hard optimization problem, with and without their native /goal mode. Fable 5 is a beast; /goal is not a game changer.