AI Coding · Launch videos on X
Product videos, demos and walkthroughs shared on X in this niche, newest first, each linking back to the original post with its live view count.
28 launch videos in AI Coding over the last 30 days.
Launch videos
65.2K14:46
412.9K0:25holy sh*t. Official Anthropic tip for Claude Code: stop burning Opus 5.5 context on tasks Haiku 5.5 can swarm, while Sonnet 5.5 builds put the architect on call with /advisor claude --advisor opus --subagents haiku Sonnet 5.5 drives the primary session on high effort, writing diffs and running test suites Haiku 5.5 subagents swarm the repo in parallel at 340 tok/s, handling file discovery and spec docs lookup Opus 5.5 stays on call in the background as the advisor, only stepping in at three critical moments: → before a plan locks: does the implementation plan miss auth invariants or schema contracts? → when a test breaks twice: are we fixing the root cause or falling into a recursive rabbit hole? → before calling done: did the full diff introduce hidden regressions or break pre-flight rules? Opus 5.5 reviews. Sonnet 5.5 builds. Haiku 5.5 swarms Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to
—2:34📣 Coming soon to GitHub Copilot: intelligent local model routing. We are excited to announce the next step in our Project HydraFusion vision. GitHub Copilot will soon be able to automatically route tasks to a local model when it's most suitable, helping you save on AI credits. https://t.co/lvjtnBswex
765.8K0:30Haiku 5.5 is now available in the Claude Platform and Claude Code. On average, it costs around 75% less to run than Haiku 4.5. It pairs well with Opus 5.5 or Sonnet 5.5 as a subagent. Use it for high-volume, cost-sensitive tasks like summaries, compactions, or database queries. https://t.co/RB9xCWo4Db
68.9K2:27I built an operating system where the AI agent isn’t another app. It’s part of the OS. Today, Herald OS is open source and you can install it yourself 🚀 It’s built around Hermes Agent by Nous Research. Talk or type to Hermes and it can work across your entire computer: • Open and use apps • Find, organize and work with your files • Remember what matters • Run routines and automations • Build software while you watch • Understand what’s happening on your screen • Work across the machine instead of being trapped inside a chat window And when something is about to make a change, you approve it first. 🎙️ Talk to your computer Say “Hey Hermes” and just talk. Native OS commands don’t need to burn model tokens. When you actually ask the agent to think, build or perform a task, that’s when Hermes gets involved. ⚡ Everyday superpowers • Select any part of your screen and ask Hermes about it • Pick a colour from anywhere • Read a QR code from your screen • Copy text from anywhere on
336K0:40
67.4K1:00
54.3K1:04here's how to build a game in Unreal Engine with Claude Opus 5.5... the trick is letting Opus work inside the live editor, but there's a smart way to set it up: - step 1: Unreal Engine 5 + the Third Person template, so you can walk and jump from minute one - step 2: enable Unreal MCP and AllToolsets in the editor, start the server - step 3: install Epic's plugin in Claude Code and have Opus read the project before it changes anything - step 4: one prompt builds a playable base level: a valley, a dirt path, a town at the end, 3 glowing collectibles - step 5: test the whole route with the default mannequin before any custom art - step 6: bring in a rigged character on the UE5 Mannequin skeleton, Opus swaps it in and wires walk, run and jump - step 7: import your forest and town assets, Opus places them along the route - step 8: refine in small batches: vegetation, lighting, a minimap, the town entrance and the rule that saves the project... a successful tool call doesn't mean the lev
98.8K0:12
147.2K0:15Introducing BlitzClean ! A free, open-source RAM monitor + disk cleaner for Mac I built it based on 3 things: - I kept running out of storage - I never knew what was eating my RAM - Memory Clean 2 stopped working for me on the macOS 27 beta (Golden Gate) What it does: - CPU, RAM and free disk in the menu bar - Ranks apps + AI agents (Claude Code, Codex, Cursor) by RAM, so you can pause or quit the ones you forgot about - Finds what fills your disk - Cleans caches, node_modules, simulators, Docker and old worktrees (you review everything first) MIT, runs 100% locally https://t.co/SLkJ2z5Ut5 Made the video with Opus 5.5 medium, what do you think ?
49.9K0:24this might be the most useful AI agent paper of 2026, and it's certified f*cking gold Wavestone AI Lab took apart Claude Code, Codex and 9 more agents every good one runs on the same 7-part harness agent = model + harness all 11 use the same 7 parts. only the size changes the 7 parts: > loop - from a plain while loop to fully replayable runs > LLM layer - one prompt template up to 29 provider profiles > tools - bash only up to 43 typed tools on demand > memory - full history up to notes kept across sessions > safety - a step limit up to rules + reviewer model + sandbox > orchestration - Aider skips sub-agents, others fork them > extensions - SKILL.md in 9 of 11, MCP in 8 it ends with a 90-line harness covering all 7 the cleanest starting point for your own agent the pages worth your time: > p.4 - the 7-part map > p.12 - 3 loop types, Claude Code and Codex as examples > p.53 - why nobody uses frameworks or embeddings > p.67 - 18 design rules > p.71 - the 90-line harness to copy
341.3K0:40Your AI isn't bad at design. It has just never seen good design. I've tested 100+ vibe coding resources this year. These are the 40 I actually kept, grouped by what you're stuck on. Bookmark this 🔖 1. 👑 https://t.co/RlChWqggj8 Why it's different from everything below: - Every one is a complete prompt, not a snippet you wire up yourself - 3 steps: copy the prompt, paste it into your AI, launch it live - 300+ award-winning prompts, all in one place - Full source code to download and edit - Works with Claude Code, Cursor or v0 Built for founders and freelancers who want award-level sites without a design team or a week of tweaking. If you only open one link in this post, make it this one. 2. https://t.co/zii2nKAKiq - design systems as markdown your agent can read 3. https://t.co/mHD5eSDPKY - ready-made prompts for dashboards and landing pages 4. https://t.co/iRLY9tbhpW - curated high-end sites 5. https://t.co/hOf1AxeaT7 - real UI inspiration mapped to prompts 6. https://t.co/bhB2Gf
47.2K0:40I've tested 100+ vibe coding resources this year. These are the 25 I actually kept, grouped by what you're stuck on. Bookmark this 🔖 1. https://t.co/RlChWqggj8 (mine) - 200+ complete build prompts for 3D, scroll-driven and cinematic websites. - Each one is a full design brief, not a component you drop in. - Copy the prompt, paste it into Claude Code or Cursor, and you get a whole animated site in minutes, not a blank page and a lot of guessing. - Built for founders and freelancers who want award-level sites without a design team 2. https://t.co/zii2nKAKiq - design systems as markdown your agent can read 3. https://t.co/mHD5eSDPKY - ready-made prompts for dashboards and landing pages 4. https://t.co/iRLY9tbhpW - curated high-end sites 5. https://t.co/hOf1AxeaT7 - real UI inspiration mapped to prompts 6. https://t.co/bhB2GfGIix - 2,000+ real product styles with typography 7. https://t.co/ZNFmqbqGsp - 2,600+ examples of how top design systems solve the same element 8. https://t.co
About AI Coding launch videos
Collected from XEvery entry is a public X post from this niche that carries a native video. We keep the post text, author, poster frame and live counters, and link to the post on X rather than re-hosting the video. This is the same sampling described in the methodology: a high-quality sample of what shipped, not a census of X.