Skip to content

Instantly share code, notes, and snippets.

View eldermoraes's full-sized avatar
🤓
Coding

Elder Moraes eldermoraes

🤓
Coding
View GitHub Profile

How I Use Claude Code — by Boris Cherny

Source: @bcherny on X · January 2, 2026
Author: Boris Cherny — Creator and Head of Claude Code at Anthropic. Former Principal Engineer at Meta. Author of Programming TypeScript.


I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.

My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.

@eldermoraes
eldermoraes / llm-wiki.md
Created April 14, 2026 03:57 — forked from karpathy/llm-wiki.md
llm-wiki

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

@Path("/mymetrics")
public class MetricsResource {
@GET
@Path("counted")
@Counted
public String getCounted(){
return "Counted";
}
@Path("/trace")
public class TraceResource {
@GET
@Traced
public String getTrace(){
return "Trace";
}
}
@Readiness
public class ReadinessCheck implements HealthCheck {
@Override
public HealthCheckResponse call() {
Client client = ClientBuilder.newClient();
Response response = client.target("https://eldermoraes.com").request().get();
if (response.getStatusInfo().getFamily().equals(Response.Status.Family.SUCCESSFUL)){
return HealthCheckResponse.up("I'm ready!");
@Liveness
public class LivenessCheck implements HealthCheck {
@Override
public HealthCheckResponse call() {
return HealthCheckResponse.up("I'm alive!");
}
}
@Path("/circuit")
public class CircuitResource {
@Timeout(unit = ChronoUnit.MILLIS, value = 500)
@Fallback(fallbackMethod = "fallback")
@CircuitBreaker(requestVolumeThreshold = 4, failureRatio = 0.5, delay = 2000, delayUnit = ChronoUnit.MILLIS, successThreshold = 2)
@GET
public String getCircuit() throws InterruptedException {
Thread.sleep(600);
return "Circuit \n";
@Path("/config")
public class ConfigResource {
@ConfigProperty(name = "config")
private Optional<String> config;
@GET
@Produces(MediaType.APPLICATION_JSON)
public Response getConfig(){
return Response.ok("Hello, " + config.orElse("Optional")).build() ;
module coffee.shop {
requires coffee.module;
}