I were 17, I'd learn how to build LLMs from scratch
Summary
Paul Graham advises that if he were 17, he would learn how to build large language models from scratch, emphasizing the importance of hands-on technical skills in AI.
Similar Articles
@Mechramc: I wrote 934 pages on how to build every layer of a large language model from scratch. Many of these concepts were new t…
Ramchand Kumaresan published a 934-page book teaching how to build every layer of an LLM from scratch, with 35 hands-on projects and a code companion.
I taught myself to code 5 months ago and built an autonomous AI red-team tester — testyourllm.com
A piano teacher with no coding background taught themselves to code in 5 months and launched testyourllm.com, an autonomous AI red-team tester that attacks any OpenAI-compatible LLM endpoint. The attacking AI, Tron, broke Llama 3.3 70B on the first try in live testing.
@RohOnChain: Don't waste 2 years learning to build LLMs like Claude & ChatGPT. Stanford just dropped a 2 hour course on how to build…
A tweet highlights Stanford's 2-hour course on building LLMs from scratch, covering tokenization, decoding, training pipelines, and architecture, noting that Anthropic pays high salaries for such expertise.
Build a LLM from Scratch using MLX
A guide on building a large language model from scratch using Apple's MLX framework.
@bibryam: How I use LLMs as a staff engineer in 2026 https://seangoedecke.com/how-i-use-llms-in-2026… The biggest AI workflow cha…
A staff engineer describes how LLM agents have evolved by 2026 to become reliable collaborators for coding, debugging, and codebase research, while humans retain responsibility for judgment and review.