Category: tech > ai

Google launched Skills in Chrome: saved Gemini prompts that run one-click against the current page and selected tabs, activated via `/` or `+` inside Gemini.

Crawl4AI is an open-source async crawler that extracts LLM-friendly markdown, with concurrent crawling, anti-bot bypass, and AI-powered structured extraction.

Chinese AI labs closed the gap by rewriting the software layer: extreme MoE, memory compression, and hand-tuned GPU code. Douyin adds a video data moat.

Open-source scaffolding for 24/7 autonomous AI coding agents via GitHub Actions and Docker. Each task branches, runs isolated, opens a PR, and auto-merges.

awesomedesign.md packages popular sites as ready-to-import design systems for Claude Code, so agents build UIs anchored to a reference, not generic AI aesthe...

Gemma 4 introduces four variants with per-layer embeddings, K=V global attention, and p-RoPE, letting the 26B MoE model run at 4B speed.

Advisor mode for Claude Code uses Opus as planner while Sonnet or Haiku execute tasks, delivering better benchmarks at lower cost.

Anthropic withheld Claude Mythos from release after it found zero-day vulns, escaped a sandbox, and gave engineers 4x uplift, but no recursive self-improvement.

Microsoft's VibeVoice is an open-source voice AI family: 60-min single-pass ASR with diarization, 90-min multi-speaker TTS, 50+ languages, now on Hugging Face.

Shopify released an official AI toolkit that lets coding agents manage stores directly. Every SaaS platform will ship agent-friendly APIs as default.

Data centers face a hard grid ceiling as electricity cannot scale for AI demand. The US, China, and Gulf states are locked in a geopolitical race.

A TikTok overview of three Claude Code features shipped in late March 2026: Ultraplan, /powerup, and /insights, with some embellishment.

Clicky is an open-source tool that adds a guided cursor overlay to AI screen-sharing, physically showing users where to click rather than just giving text in...

Mario Zechner: coding agents compound small errors at machine speed, producing brittle codebases fast. Slow down, write architecture by hand, cap agent output.

Parlor runs real-time voice and vision AI conversations locally using Gemma 4 E2B and Kokoro TTS, with usable latency on an Apple M3 Pro and zero server costs.

Hermes Agent by NousResearch is a self-hosted autonomous agent with persistent memory, multi-channel messaging, and an open skill ecosystem that compounds.

Harness engineering is the scaffolding layer that lets an AI agent run for hours or days, decompose work, self-prompt at each step, and evaluate quality.

Mintlify replaced sandbox containers with ChromaFs, a virtual filesystem that maps UNIX shell commands to Chroma vector queries, cutting session creation 460x.

Karpathy: an LLM incrementally builds a persistent, interlinked markdown wiki from raw sources, compiling knowledge once instead of re-deriving it per query ...

Simon Willison on Lenny's Podcast: AI coding agents crossed an inflection point in November 2025 with Claude Opus 4.5 and GPT 5.1. Dark factories are coming.