Topics

LLM

Every article on LLM published on this blog, newest first: 5 in total, written by Ramón Chancay.

5 articles on LLM

Illustration of sanitype: a payload crosses a boundary and comes out with its sensitive fields masked, plus a report of what was touched

AI7 Sep 202620 min read

Sensitive data out of the prompt: a TypeScript library written in 39 minutes from its specification

sanitype redacts, masks or drops sensitive data inside the process before a payload leaves for an LLM, a log sink or a third party. How it is implemented in TypeScript.

Execution sandbox illustration: the model's text enters an isolated enclosure with a timer, passes through four filters, and comes out as a classified observation

AI30 Jun 202621 min read

The sandbox in an agent loop: from the model's text to a reliable observation

The sandbox in an agent loop turns the model's text into a reliable observation: extract the code from the prose, check that it parses, run it with a timeout, and isolate the process.

Agent loop illustration: a goal enters a cycle of decide, act, and observe that repeats until a stopping condition

AI29 Jun 202612 min read

What an agent loop is (and isn't): state, action, stop

What an agent loop is and isn't: its three components—state, action, and stopping condition—and why 'build me an app' is input for a chat, not an agent.

Model routing illustration: a request is split across several models, with most of the traffic going to the main model

AI29 Jun 202625 min read

Model routing with OpenRouter and DeepSeek to cut costs without losing quality

How I routed models in production with OpenRouter, using DeepSeek for the bulk of traffic and premium models only where it matters, cutting LLM costs without degrading quality.

Automation29 Jun 202616 min read

I automated a news site with n8n: from 20 RSS feeds to WordPress drafts

How I built an n8n pipeline that reads 20 RSS feeds, deduplicates with Postgres, curates and rewrites with tiered AI, and leaves the article as a WordPress draft with an image and a Telegram alert.