AI on X
AI people on X: ideas, agents and working software
A model demo, a working app and a research paper answer different questions. Meet the people behind them, inspect what they made and choose a useful starting material.
Start with a question
A useful first work is a better starting point than a long list of names.
Understand language models
Start with explanations and small implementations, then read the original Transformer paper.
Foundations & explanationsLook inside training
Explore training recipes, model checkpoints and the systems that make computation faster.
Training & model systemsEvaluate a model claim
Compare reasoning methods, factual-answer tests and the questions a benchmark can answer.
Reasoning & evaluationBuild a first product
Explore prototypes and shipped products, with the author’s explanation of how they were built.
Builders & productsWork with coding agents
Compare how people supply context, break up tasks and use agents in their everyday work.
Agent workflowsUnderstand and check the code
Read about tests, code review and the tradeoffs of delegating implementation to a model.
Engineering & evaluationExplore a reading list
Meet different approaches to the same subject.
- AI reading listVibe coding & coding agents
Meet people building with LLMs: product demos, coding-agent workflows and practical ways to understand and check generated code.
10 selected people.
Open the selection - AI reading listLLM research & explanations
Find LLM researchers through their original work: Transformer explanations, training recipes, model systems, reasoning and evaluation. Choose a useful first read.
12 selected people.
Open the selection
People and their work
21 profiles with original works and project context.
-
Practical ways to plan, inspect and test software made with coding agents, from a small change to a team's development process.
Explore their work -
The product and infrastructure thinking behind Replit's move from a coding editor to building software through natural language.
Explore their work -
Explains how language models change software development, from his original description of vibe coding to experiments where an agent changes training code and measures the result.
Explore their work -
Explains the design of a coding agent and shares how he uses it in everyday work, including project instructions, reusable commands and ways to verify a change.
Explore their work -
Created Keras and ARC, and examines how to distinguish learned task performance from the ability to solve unfamiliar problems.
Explore their work -
Explores coding agents as repeatable systems, from the Ralph loop to a Lisp application that acquires new capabilities through conversation.
Explore their work