Pinned Tweet
Andrej Karpathy spent 70 minutes explaining how top AI users actually work with LLMs.
And most people are overcomplicating it.
Bookmark it for later.
Solid roadmap for learning agentic engineering from scratch.
@bot : always-on AI teammates with their own cloud computer that stay signed into your tools
@DevinAI : the ai software engineer that codes, tests, and ships autonomously
@tavilyai : search, extract, crawl, and research apis built for agents
@p0 : high-accuracy web search, extract, and deep research for agents
@PlasmaAI : radio (agents talk to each other in real time)
these cover the practical stack most people actually use
If you’re trying to learn agentic engineering, here is a roadmap to help you figure out where to start.
agentmax.space
If you’re trying to learn agentic engineering, here is a roadmap to help you figure out where to start.
agentmax.space
this is pure f*cking treasure.
DISTRIBUTION matters. sarah built an app her followers actually wanted and reported $300k MRR two months after launch.
here is a broke down how her videos turned viewers into paying customers.
why pay for a big model when your agent keeps doing the same job.
i’d try a smaller model trained to find customer problems and quote their feedback accurately.
check this out: github.com/overmind-core/ove…
@OvermindLab lets you train models on your agent’s data and own the weights.
in their contract test, 1,000 questions cost $1.03 vs $20.94 on a frontier model. about 20x cheaper.
🤝 Paid partnership
Overmind turns anyone into an AI lab.
• Builds a context graph from code and traces
• Curates training and eval datasets
• Evaluates prompts and models
• Trains smaller, specialized models
github.com/overmind-core/ove…
i just gave claude one of my fav pinterest image and it turned that into this.
catbridge.vercel.app
i made a tutorial on how to use grok bot for beginners
youtu.be/e0tp2RAMH9k?si=99bD…

















