Category: tech > ai

Darkbloom routes encrypted AI requests to idle Apple Silicon Macs, the Airbnb of GPU compute. ~50% cheaper than OpenRouter, with hardware attestation.

Fireworks AI is an inference platform for open-source generative models, marketed with latency drops from 2s to 350ms but no pricing or benchmarks.

Ollama wraps llama.cpp but skipped attribution, forked ggml badly, and pivoted to VC-backed cloud. llama.cpp delivers up to 1.8x throughput on the same hardw...

Google shipped a native Gemini macOS app with one-keystroke Option+Space access and optional screen sharing. Free, Apple Silicon only, macOS Sequoia 15.0+.

exo clusters Apple Silicon Macs into a distributed AI inference pool, running DeepSeek v3.1 671B and Kimi K2 locally with RDMA over Thunderbolt 5.

Graphify builds a multi-modal knowledge graph (Tree-sitter + LLM extraction, Leiden communities) so AI coding assistants grasp large codebases at 71x fewer t...

Cloudflare Agent Lee is an in-dashboard AI assistant using Codemode to turn MCP tools into a TypeScript API, with Durable Object proxy gating writes by elici...

A 30-second rundown of Opus 4.7: gains on coding benchmarks, 3x higher screenshot resolution, new X high reasoning tier, and a /ultra-review slash command.

Alibaba open-sourced Qwen3.6-35B-A3B, a 35B MoE with 3B active params scoring 73.4 on SWE-bench Verified and integrating with Claude Code via OpenAI-compatib...

Claude Code /routines (via /schedule) runs scheduled tasks on Anthropic's servers, not your terminal. Triggers support cron, API, or GitHub webhooks.

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.