Give Smart People the Tools to Do Smart Things

Gemini Code Assist will be shut down on July 17

Alibaba to ban Claude Code in workplace over alleged backdoor risks, source says

14× faster embeddings: how we rebuilt the ONNX path in Manticore

The Safari MCP server for web developers

Right to Local Intelligence

The short leash AI coding method for beating Fable

Claude-real-video － any LLM can watch a video

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

Since Linux 6.9, LUKS suspend stopped wiping disk-encryption keys from memory

Launch HN: Manufact (YC S25) – MCP Cloud

No LLM Code in Dependencies

The primary purpose of code review is to find code that will be hard to maintain

CursorBench 3.1

Kimi K2.7 Code is generally available in GitHub Copilot

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

Fable 5 Is Back

ZCode: Claude Code from the Makers of GLM

Most rewrites serve the engineer, not the business

What to learn to be a graphics programmer

Monetization Gateway

Claude Code Just Got 5x More Expensive

I ported Kubernetes to the browser

Claude Sonnet 5

We Are the Last People Who Know How It Works

Nano Banana 2 Lite

Claude Code Is Steganographically Marking Requests

Popping the GPU Bubble

LongCat-2.0, a large-scale MoE model with 1.6T total and 48B Active

Amazon Is Awash with AI-Written Guideslop for Games That Aren't Even Out

Working With AI: A concrete example

A field guide to the modern front end for developers who hand-wrote HTML

Mag 7 starting to underperform [pdf]

Tidal AI Policy

Herdr: Agent multiplexer that lives in your terminal

HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

Xonaly – Canada's Independent Search Engine

Librepods: AirPods liberated

The cost YAGNI was never about

Tokenmaxxing is dead, long live tokenmaxxing

Reflections on software engineering in the age of AI

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

Running a software jam in a world of slop

DeepSeek open-sources inference optimizations with 60–85% faster generation [pdf]

The Exhaustion of Talking to a Tool

Incident CVE-2026-LGTM

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

Why current LLM costs are not sustainable