Machine Learning

I wrote my first app with GPT3 and these are some of my notes and my takeaways. I always wanted to try GPT3. I bookmarked a YouTube tutorial to try GPT3 with Python. And sure enough I never started it. (If only I could learn from bookmarks!!) Then chat GPT…

Announcing our fundraise Today, I’m thrilled to announce that we’ve raised a $5M seed round led by Diana Kimball Berlin at Matrix. Some great founders and operators are also participating, from companies like Snorkel AI, Tesla, and Google. …

Using contextual bandits will help surface attractive items you could have otherwise missed — Getting started If you have never addressed a ranking problem before, it can seem a bit overwhelming. You might even be asking yourself, “Where can I start?” …

TL;DR: Here we show how image search can be evolved to add localization and re-ranking by leveraging Marqo, yolox, CLIP and OWL-ViT. Adding the extra dimension of localization can improve retrieval performance and enable new use cases for image search while also helping with explainability. Re-ranking with an open vocabulary…

Just like data scientists, Spider-Man is a force for good, but often misunderstood. He is basically a big spider: brave, strong, and smart. In this article, we will explore his abilities, using real science (as much as possible), to answer a couple of questions: 1. How strong is Spider-Man’s silk…

What is it? ChatGPT is a state-of-the-art natural language processing (NLP) model developed by OpenAI. It is a variant of the popular GPT-3 (Generative Pertained Transformer 3) model, which has been trained on a massive amount of text data to generate human-like responses to a given input. How does it work? Unlike traditional NLP models that rely…