全部 AI 动态

Copy and paste this into your codex: “Look through my recent Codex sessions and identify repeated workflows or repeated asks. For anything I keep doing manually, suggest: 1. a skill if it is a reusable workflow 2. a custom subagent if it is a bounded role or investigation task Focus on practical things like CI failures, PR reviews, changelogs, docs updates, release prep, debugging, and test triage. Create the useful ones only. Keep them simple.”

自动模式的两项更新： · 现已在 Pro 套餐中可用 · 除 Opus 4.7 外，现也已支持 Sonnet 4.6 按 Shift+tab，让 Claude 运行。

I built "zero2claude", a free course that takes people from zero terminal experience to shipping with Claude Code. The curriculum goes from absolute zero → software basics → Claude Code fundamentals → advanced usage. No shortcuts, no assumptions. 17,000+ students. 7 languages. ~500 active hourly. No marketing. No ads. Pure word of mouth. The entire platform? Built and operated by one person with Claude Code. Lighthouse audit: ✅ Performance : 96 ✅ Accessibility : 100 ✅ Best Practices : 100 ✅ SEO : 100 Production stats: ~6.4M requests/day. 74 req/sec sustained. <0.003% error rate. Claude Code doesn't just write code. It builds production-grade, scalable products. The best way to grow Claude Code adoption isn't to simplify the tool. It's to level up the people. Give fishing rods, not fish. Free. No paywall. My contribution to the community. Link in the comments 👇

I built "zero2claude", a free course that takes people from zero terminal experience to shipping with Claude Code. The curriculum goes from absolute zero → software basics → Claude Code fundamentals → advanced usage. No shortcuts, no assumptions. 17,000+ students. 7 languages. ~500 active hourly. No marketing. No ads. Pure word of mouth. The entire platform? Built and operated by one person with Claude Code. Lighthouse audit: ✅ Performance : 96 ✅ Accessibility : 100 ✅ Best Practices : 100 ✅ SEO : 100 Production stats: ~6.4M requests/day. 74 req/sec sustained. <0.003% error rate. Claude Code doesn't just write code. It builds production-grade, scalable products. The best way to grow Claude Code adoption isn't to simplify the tool. It's to level up the people. Give fishing rods, not fish. Free. No paywall. My contribution to the community. Link in the comments 👇

Qwen 3.7-max beats Opus 4.7 and GPT-5.5 We tested three frontier models on a real agentic task: write a Tetris bot that plays the game and trains itself. Each model could read its own code, run benchmarks, and rewrite itself across 10 iterations. Then we compared the final bots head to head. Qwen 3.7-Max: training cost $1.32, bot improvement +56% Claude Opus 4.7: training cost $12.15, bot improvement +28% GPT-5.5: training cost $2.85, bot improvement +7% Qwen won on every dimension - biggest jump, 9× cheaper than Claude, 2× cheaper than GPT. Long agentic loops is where Qwen Max actually delivers.

The @code team released a new Introduction to Agent-First Development series. It breaks down these 5 pillars behind great agent results 🧵

the most used skill internally at cursor right now /thermo-nuclear-code-quality-review - deletes complexity instead of moving it - blocks files over 1k lines - flags thin wrappers and leaked logic - rejects PRs that work but make code messier

If you are managing multiple machines across clusters and farms, you could ask Grok Build to spin off a sub-agent SSH tunnel into the machines while interacting with tmux sessions for you. Thanks to @skcd42 for the tips. Now I can fully live inside the main Grok Build instance without additional tabs to other clusters.

http://x.com/i/article/2057172544277606401

You need to set up this Codex system I have Been taking advantage of their new remote features and my productivity has 1000x'd I have one device (Mac Studio 1) as my main dev machine. That's where all code is written Then all my other devices (iPad, iPhone, Mac Studio 2, 2 Mac Minis) are nodes I send commands from No matter which device I'm on, no matter where I am in the world (could be at the grocery store, in bed, Japan, on the toilet, by the pool, on the road using FSD) I have code written in one place Made coding big projects SO much easier Here's what I'd do if I were you Choose one device you have (preferably a desktop device like Mac Mini or Mac Studio) Make this your main dev device. Make sure it never turns off and never goes to sleep Go into Codex app then settings on that device. Go to connections > control this Mac. Turn that on Then go into every other device you have, mobile, desktop, whatever, and go into Codex settings and enable control other devices Also download Tailscale on every device. This will allow you to create a private network that will allow your other agents (OpenClaw or Hermes) to jump between computers and make changes when necessary You now have a super powered AI private network where you can code or get work done from any device anywhere in the world Promise this 1000x's your productivity

It was fun trying to get this... ideating with AI and and crafting the prompt. Ref images + the Prompt. 🙌😅 { "title":"Soccer Match Selfie Video", "style":"Ultra realistic smartphone selfie footage, documentary realism, authentic human interaction, natural imperfections, NOT polished commercial footage.", "character_consistency":"Use ALL FIVE attached character refs exactly throughout the video. Preserve accurate face, hairstyle, age, skin tone, freckles, glasses, sideburns, ethnicity, smile shape, and clothing style.", "characters":[ "South Asian male, curly dark hair, black round glasses, trimmed beard, oversized dark sweatshirt.", "East Asian female, long straight black hair, freckles, pastel casual outfit.", "White middle-aged businessman, short brown hair, receding hairline, navy casual jacket.", "White rugged male, thick dark hair, dramatic sideburns, black bomber jacket.", "White woman, shoulder-length brown hair, cheerful smile, black casual outfit." ], "environment":"Huge modern soccer stadium at night, bright floodlights, LED scoreboard glow, cheering crowd, green football pitch visible.", "camera":"Front-facing smartphone camera, handheld shaky motion, wide-angle selfie distortion, autofocus hunting, motion blur, exposure changes, cropped faces, imperfect framing.", "actions":[ "calm pre-game selfie", "laughing together", "singing chants", "near-goal anticipation", "dramatic reactions", "goal celebration", "jumping and screaming", "happy exhausted ending selfie" ], "behavior":{ "south_asian_male":"holds phone and reframes constantly", "east_asian_female":"warm natural smile and laughter", "businessman":"calm then emotional", "rugged_male":"intense dramatic reactions", "white_woman":"points excitedly toward field and camera" }, "wardrobe":"hoodies, soccer scarves, oversized sweaters, windbreakers, casual jackets, dark streetwear.", "prompt":"Ultra-realistic handheld selfie video of five friends attending a packed nighttime soccer match. The South Asian man films with a smartphone while all five crowd naturally into frame. They laugh, chant, joke, react to near goals, scream after scoring, wave scarves, bounce with the crowd, and celebrate wildly together. Realistic stadium lighting, social-media-style footage, immersive sports atmosphere, authentic candid energy." }

Gemini 3.5 Flash ARC-AGI (Verified) ARC-AGI-2: - High: 72.1%, $0.85 - Minimal: 8.9%, $0.11 ARC-AGI-1: - High: 92.5%, $0.42 - Minimal: 48.8%, $0.06 Gemini 3.5 Flash is on par with GPT-5.5 (Medium) on ARC-AGI