Thoughts, lessons, and the occasional rabbit hole
Using and understanding AI, from machine learning concepts to AI-assisted work.
5 articles
I used to know what keeping up with technology meant. In Python or data science, it meant reading release notes, trying a few libraries, following a few people whose judgment I trusted and occasionally reading a paper that seemed relevant. There was always more to learn, but the shape of the work was understandable. Most changes were incremental. The important developments were usually visible. If I fell behind for a few weeks, I could catch up.
I wanted to create a personalized children's picture book as a gift for my friends' daughter.
I spent about a week asking AI to redesign my chocolate database webapp. It kept making nicer versions of the same not-good interface. The useful shift came when I stopped showing the AI the app I already had and started describing the dataset, the people using it, and the experience I wanted. That sounds like a small prompting change. For me it changed the whole shape of the result.
I was recently invited to join a panel discussion among developers to dispel the myth of the typical BS Buzzword Bingo around machine learning and AI. In this blog post, I will share some buzzwords we talked about with a little description and links. Ooops, I already used some buzzwords. So let’s start.
Humans intuitively understand the meaning of words: Which words are similar, opposites or related to each other? But our machine learning models do not have this intuition. Word embeddings are numeric vectors that represent text. These vectors are learned through neural networks. The objective when creating these embedding vectors is to capture as much “meaning” as possible: Related words should be closer together than unrelated words. Also, they should be able to preserve mathematical relationships between words such as