Topics

LLM

Every article on LLM published on this blog, newest first: 6 in total, written by Ramón Chancay.

6 articles on LLM

Jev illustration: a state enters a decision node and comes out as three typed values, a yes or no, a choice and a score, with no text in between

AI23 Sep 202613 min read

What is Jev: TypeSafe AI's model that decides instead of writing

What is Jev, TypeSafe AI's System One model: it returns typed decisions with probabilities instead of text. How to call its API, what it costs, when to use it.

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 in process before a payload reaches an LLM, a log sink or a third party. How it is built 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 LLM-generated code into a reliable observation: extract the code, check it parses, run it with a timeout, isolate it.

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: DeepSeek for the bulk of traffic, premium models only where it matters, lower LLM costs, same quality.

Automation29 Jun 202617 min read

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

How I built an n8n pipeline: 20 RSS feeds in, Postgres dedupe, tiered AI rewrites, and out comes a WordPress draft with an image and a Telegram alert.