@free_ai_guides

Article

One command. Two hours of autonomous work. A finished brief waiting when I got back....

@karpathy

Thread

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as mar...

@undefinedKi

Article

Ask Claude about your company, your notes, or your files, and it draws a blank. It never saw them. It only knows what it learned in training, and your stuff wasn't part of that....

@choopyplug1

Article

Most developers still prompt their coding agent by hand. Type, wait, read the diff, type again. <b>You are the loop.</b>...

@ChrisHayduk

Article

In July 2024, DeepMind unveiled AlphaProof — an AlphaZero-inspired agent that constructs arguments in Lean, a programming language for proofs. It broke new ground in mathematical performance, achieving a silver medal in the 2024 International Math Olympiad....

@AnatoliKopadze

Article

Everyone is talking about AI agents. But if you ask most people what an agent actually is, you get a vague answer about "AI that does things autonomously."...