AI, data, agents, reliability, context, and technical architecture.
Matt Rickard has a concise overview of Chain-of-thought: the design pattern of having an LLM think step by step. To summarize, the four mentioned approaches from simpler to more nuanced are: 1. Add "Let's think step-by-step" to the prompt. 2. Produce multiple solutions, have the LLM self-check on each one, pick
Every classification task is linearly separable in the right feature space. This statement is a clue to building ML solutions that scale to many different use cases. Here’s a visual explanation. Say you have data points in a given two-dimensional vector space. If you can use a straight line to separate the two classes, the dataset (and prediction
Lately, Twitter has been full of the 2020 US election, which has displaced everything interesting. That means it’s a good time to blog. I’ve recently been reading James C. Scott’s Seeing Like a State, which manages to combine forestry, agriculture, and land/city planning into a history of top-down planning. One thing that stuck with me
A few years ago at Starship, I contributed to the Data is the Specification [http://dataisspec.github.io/] manifesto. The core idea is that it's better to solve problems directly against a collection of examples, as opposed to trying to generalise the problem first and then solving the general problem. Typically you would run an employee engagement survey,
Today I gave a short talk at Digital Agenda for Estonia 2021+, the Ministry of Economic Affairs and Communications event where the country's next ten years of digital policy are being planned. I work at Veriff and have no policy experience whatsoever. It's twelve minutes long and the argument is that the state should build APIs
