Does code cleanliness affect coding agents? A controlled minimal-pair study

Dungeon Proof Crawler: learn how to write proofs with RPG

Mark Zuckerberg tells staff that AI agents haven't progressed enough

Knowledge Should Not Be Gated

The Log is the Agent

Potential session/cache leakage between workspace instances or consumer accounts

Agentic coding notes from Galapagos Island

Leanstral 1.5: Proof abundance for all

Claude, please stop trying to memorize random crap

Costco is the anti-Amazon

It Still Can't Do My Job: Four Years of Moving Goalposts (2022–2026)

Give Smart People the Tools to Do Smart Things

Zuckerberg 'Admits' Meta's Layoffs Were Ineffective

The short leash AI coding method for beating Fable

Claude's AskUserQuestion: "No response after 60s – continued without an answer"

CursorBench 3.1

Senior SWE-Bench: open-source benchmark that assesses agents as senior engineers

Fable 5 Is Back

Claude Fable 5 Promotional Access

ZCode: Claude Code from the Makers of GLM

Weave Robotics launches Isaac 1, a $7,999 home robot with Fall 2026 deliveries

Claude Fable 5 export control lifted

Claude Code Just Got 5x More Expensive

Claude Sonnet 5

Claude Science

Claude Code Is Steganographically Marking Requests

Micro-Agent: Beat Frontier Models with Collaboration Inside Model API

Ornith-1.0: self-improving open-source models for agentic coding

Mag 7 starting to underperform [pdf]

Herdr: Agent multiplexer that lives in your terminal

Xonaly – Canada's Independent Search Engine

Do LLMs pass the mirror test?

GLM 5.2 beats Claude in our benchmarks

I used Claude Code to get a second opinion on my MRI

Tokenmaxxing is dead, long live tokenmaxxing

A way to exclude sensitive files issue still open for OpenAI Codex

Wayfinder Router: deterministic routing of queries between local and hosted LLM

Anonymous GitHub account mass-dropping undisclosed 0-days

Post-Mythos Cybersecurity: Keep calm and carry on

Anatomy of a Failed (Nation-State?) Attack

The Exhaustion of Talking to a Tool

Captcha proves you're human. HATCHA proves you're not

OpenAI to Stagger Release of GPT 5.6 at Request of U.S. Government

Bible as RAG Database

I rewrote PostHog's SQL parser, 70x faster, while barely looking at the code

Computer use in Gemini 3.5 Flash

The CAPTCHA arms race: from distorted text to browser identity

RubyLLM: A Ruby framework for all major AI providers

Haystack: Open-Source AI Framework for Production Ready Agents, RAG

Qwen-AgentWorld: Language World Models for General Agents