To go beyond vibe coding, don't learn syntax, learn infrastructure

WorldGen seems cool... Opus 4.5, can you build this?

Want to create game assets with AI? In this tutorial I share some tips for how to do this with general-purpose AI platforms like Replicate and OpenRouter, rather than game-dev specific services The focus is on building your own asset pipeline youtube.com/watch?v=h-vZ5k…

npx supabase migration list supa useful if you can't figure out what's going wrong with your migrations supabase.com/docs/reference…

how many apps can you vibe code at the same time?

free canvas drawing tool - try it out! (or just build your own) hackerpad.ink

Hey everyone! Agentic programming can be risky, especially in YOLO mode - do it safely by developing inside a docker container. Here's a free tool that makes it easy to manage your containers for agentic programming. (think slim DockerDesktop) github.com/Launchable-AI/…

The Vibe Coding Promptuctivity Time Dilation

Vibe coding productivity tools is the new dotfile tweaking

build your own darn tools

Building software for yourself to use is 100x easier than building for customers prediction - the norm in 2026 will be vibe-coded productivity tools that people build for themselves, to match their specific needs SaaS is a function of limited engineering brain - not needed now

Just released v2 of Video Insight Pro! check it out if you're doing video analysis videoinsight.pro

Chat is Cheap - if you're not inferencing, you're losing

Run AI agents in a container! Docker containers let you can use YOLO mode without fearing that the agent will delete your hard drive. 😨 We built Agent Containers to make it a bit simpler github.com/Launchable-AI/… Just docker + AI niceties: - MCP search - volumes - ports - 👀

AI/Agentic Development Tip - if you're stuck trying to fix a bug, tell the agent to write itself a script and iterate on the solution up to 5 times. eg - you are calling an API and need to parse the response, but keep getting errors. Get the agent to iterate on it

just one more prompt...

Pitch your software security solution / team below 👇 We're on the hunt for great external auditing, pen-testing, and compliance teams 🕵️‍♂️ Reach out if you're a Canadian security firm

LLMs are terrible at naming products / companies

Agentic dev tip - when working on your codebase, get the agent to code scripts it can use to test its work. Think unit tests, but for agents. This allows the agent to iterate more effectively while working on bugs. This is a similar idea to code gen vs MCP

If you want a sense of how big the internet is, try getting a .com