Guy good news register on https://t.co/ezknnhp2DC be experience prop firm trading like never be for,
Great pricing for all sorts of accounts
@constantfunded
Don't waste 2 years learning to become an AI agentic engineer in 2026.
Andrew Ng, the godfather of AI, gave the complete playbook to become one from scratch.
1 hour course. Free:
โข 00:00 - AI agent basics
โข 12:12 - AI Agentic workflows & design patterns
โข 53:27 - Practical tips for building AI agents
โข 1:20:30 - self-improving AI agent loops
โข 1:30:19 - multi-agent AI systems
I watched it last night.
Halfway through, I realized I could get into Anthropic in weeks, not years.
Bookmark now. Watch it. Then build your own AI agent.
Don't spend 2 years learning how Claude and ChatGPT actually work.
Stanford just dropped a 2.5 hour course on building an LLM from scratch.
0:00 - LLM tokenization
25:03 - how LLMs decode a prompt
34:44 - the training pipeline
1:14:47 - the architecture, from scratch
look at the first one, because it is the section everyone skips.
Text โ Tokens โ IDs โ Vectors
by the time the model sees your prompt it is not text. it is integers, split where you would not expect.
that is why renaming a tool changes which one gets called, and why one character moves the whole result.
reading your prompt is the old mental model. reading what was sent is the new one.
Anthropic pays $750,000 a year to engineers who understand this layer.
watch it today, then read the eval setup below.
Apple fired Steve Jobs.
Soon after, he gave one of the most candid 60-minute business lectures you'll ever watch.
No PR script. No polished image. Just lessons on building products, leadership, failure, and starting over.
Watch this instead of Netflix tonight.
Bookmark it. You'll come back to it.
Google put out a free 1-hour long course on building agents from scratch and it's actually good
00:00 - your first agent, built from nothing
08:24 - giving it memory that actually persists
28:34 - loops that keep running for hours without you
40:04 - mcp vs api, and when to build your own
1:00:22 - stitching multiple agents together
Most people building agents right now don't actually get this stuff. watch it, then read the loop breakdown below