#ai on the community blog
Community posts tagged ai.
- Tools
Ollama: run open LLMs locally for development, privacy and offline work
Ollama makes running open models on your own machine a one-command job and exposes them through a local API. Here is the workflow, how to call it from code, and what to expect on real hardware.
- Tech articles
Vector embeddings explained for developers: similarity, normalisation and the mistakes that hurt search
What an embedding really is, how cosine similarity and dot product relate, why you should normalise, and the practical mistakes that quietly make semantic search worse.
- Tech articles
Prompt injection: practical defences for LLM apps that read untrusted text
Any LLM feature that reads emails, web pages or user uploads can be steered by text hidden inside them. Here is a layered set of defences that work in production, and why no single one is enough.
Write for RecallRun
Start writingShare a tech article or a tool you built. Every post is checked and reviewed before it goes live.