Get your bearings on X.
The conversations move fast. Start with the language, get to know the people and learn to follow a claim back to its source.
Start with the basics
New to a subject on X? Get your bearings, choose a few useful accounts and understand the language in your feed.
-
How to evaluate an AI application on your own task
Define a useful success test, trace a published failure and compare fixes through Hamel Husain, Jason Liu, Eugene Yan and Chip Huyen.
Published
-
Before you download a local LLM
Separate model from runtime, budget memory beyond the file and plan a repeatable local-model test with original work from five useful authors.
Published
-
How to write an AI image-editing brief and check the result
Define what changes, what stays and how to check an AI image edit. A published pancake example shows why those decisions matter.
Published
-
From a vibe-coded prototype to a checked change
Use a small search-filter bug to connect a requirement, code walkthrough, failing case and focused fix, with work from Simon Willison and Addy Osmani.
Published
-
How to read an LLM research result: a worked example
Read a Tülu 3 experiment from table to conclusion: compare training settings, interpret the score and keep the limits, with useful authors to read next.
Published
Read between the lines
A label or a demo is only a starting point. Follow the source, the incentives and the claim behind the post.
-
Twitter shadowban test: check search, replies and labels on X
Test an X (Twitter) shadowban yourself: search suggestions, from: searches and replies from a second account, X's own labels, and innocent causes to rule out.
Published
-
An AI agent demo checklist: tools, state and success
Assess an AI agent demo through its tools, state, access and checked outcome. Read a published database-error recovery and plan the next useful test.
Published
-
Prompt injection in AI agents: follow the tool calls
Trace a published prompt-injection attack from a code comment to a private Slack read and public post, then inspect the permissions behind the tool calls.
Published