Data Analytics, AI & Automation Specialist
A manufacturer of card shuffling machines for casinos asked us to develop a fast algorithm capable of classifying poker cards with inference time below 150ms per card. First attempt: Fine-tuning Image classification on a Raspberry Pi can be quite simple,
An occupational hazard of computer savvy people (me included) is that we get approached by characters such as Ed the Entrepreneur, who has a “great business idea that is very easy to build”. Sometimes with good intentions, sometimes less so.
I was approached once by an entrepreneur, let’s call him Ed. Ed wanted me to build an app that detects car engine failures. He was a trust fund boy who was annoyed by the fact that some of his many
Fine tuning ChatGPT is super easy. The most annoying part is to transform the data to the desired format. You need to provide a file where each row is a small JSON object consisting of three things: a prompt to
One can, often successfully, force ChatGPT to speak other languages simply by tricking the prompt. If you are a Czech speaker, copy and paste the code below (requires LlamaIndex) and OpenAI’s API) to get yourself pampered by grandma. import os
An important use case of large language models (LLMs) is to answer questions from a specific corpus. Tools like ChatGPT are great for conversation, but not so great for retrieving information from a specific set of knowledge. To cover up