Explore
The Assist @ Things Of Interest
At work we recently started experimenting with generative AI for assistance with programming. We have a...
The Sweet Spot - Maximizing Llama Energy Efficiency · Jacques Mattheij
tldr: limit your GPUs to about 2/3rd of maximum power draw for the least Joules consumed...
How Meilisearch Updates a Millions Vector Embeddings Database in Under a Minute
This is part 4 of a series of blog posts. You can find part 1, part...
Semgrep: AutoFixes using LLMs · Choly's Blog
Sun, Mar 24, 2024 Semgrep is an incredible tool that allows you to search code by...
Redesigning OLTP for a New Order of Magnitude
Greef: The world is becoming more transactional, from servers to serverless, and per second billing. You...
Claude and ChatGPT for ad-hoc sidequests
22nd March 2024 Here is a short, illustrative example of one of the ways in which...
pgvector vs. pgvecto.rs in 2024: A Comprehensive Comparison for Vector
pgvector and pgvecto.rs are both vector search extensions designed to enhance the capabilities of PostgreSQL. These...
Thoughts on cloud GPU providers? | Lobsters
Looking to get advice and additional insights on hosting large language models. I have gathered some...
Cataloguing my vinyl collection with computer vision | James' Coffee Blog
Every so often, a daunting thought comes to mind: I really should make a list of...