Fable 5 vs. GPT-5.6 Sol on an NP-Hard Problem: Does /goal help?

Claude Code: Anatomy of a Misfeature

The human-in-the-loop is tired

LM Studio Bionic: the AI agent for open models

$100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

Kimi K3 is now #1 in the Front end Code Arena with 1679 pts, surpassing Fable 5

Agent-talk: Enabling coding agents to work together

Schema Harness Achieves ~99% on Arc‑AGI‑3 Public

Kimi K3 is now live

Grok Build is open source

Inkling – Open-Weights 975B Parameter LLM

Open-source memory for coding agents, synced over SSH

Codex Micro

When A.I. is a member of the family

Towards a Harness That Can Do Anything

I tricked Claude into leaking your deepest, darkest secrets

Solving 20 Erdős Problems with 20 Codex Accounts Running in Parallel

Bonsai 27B: A 27B-Class model that runs on a phone

Launch HN: Agnost AI (YC S26) – Extract user feedback from agent conversations

The Agentic Loop: Three loops in a trench coat

Proof of care in the age of AI

Guardian Angels: LLM Personalization for Productivity and Security

Coding agents think ahead of time

How to stop Claude from saying load-bearing

Punch yourself in the face with reality

Codex starts encrypting prompts, uses ciphertext for inference instead

The Economics of Recursive Self-Improvement [pdf]

Claude is just Mr. Meeseeks

A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI

The One-Step Trap (In AI Research)

I love LLMs, I hate hype

Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

Fable extended until 19 July

Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

Old and new apps, via modern coding agents by Terry Tao

Why Write Code in 2026

Stop Telling Me to Ask an LLM

AI 2040 and the cult of intelligence

Write code like a human will maintain it

ChatGPT Work

Launch HN: Context.dev (YC S26) – API to get structured data from any website

Hy3

Opinionated and easy Pi.dev configuration

Why we're moving off Cloudflare Durable Objects

Muse Spark 1.1

MIRA: Multiplayer Interactive World Models Trained on Rocket League

GitLost: We Tricked GitHub's AI Agent into Leaking Private Repos

GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday

We charge $10k a week to delete AI-generated code

AI Meets Cryptography 1: What AI Found in Cloudflare's Circl