Posts

In this article I talk about the implementation of the paper “Verifiable Reinforcement Learning via Policy Extraction” by Osbert Bastani et al.

Here I talk about how to get the most out of your conversational AI and customer support by having your AI suggest likely responses and then training it on the selection that customer support makes. Links: Talk: https://www.youtube.com/watch?v=MCXumfwcmXE Implementation Blog post: How to level up your customer support and AI using Airy and Rasa X

The Covid-19 virus has turned the beginning of 2020 into a surreal nightmare. The world is struggling to maintain a confident response and not let the disaster movies of the last decade become a reality. If you haven’t read it yet or don’t think the situation is extremely serious I recommend that you check out this article. Like many of my peers, I have been in self-isolation for weeks now. While our problems pale in comparison to those of the brave health care workers fighting at the frontlines we bear an inescapable sense of dread and helplessness by having to watch the infection spread....

You are building a product and you want to move fast. But you can’t just launch your MVP without auxiliary tools to help you learn and grow it. You will want to track visitors to understand, where they are coming from, track users to understand how they are using your product and can you really call it a landing page, without a Newsletter Subscription Button and an obnoxious chat window popping up?...

When I started university the “The Social Network” movie had been out only four years. And although this feels like an eternity as far as hype cycles go, you would be hard pressed to find an economics or CS student, who has not fantasized about rising above his peers by hacking together the next game-changing tech solution. And it’s not just some romanticized career path for millennials: Institutions are catching up, too....