posts

During lunch breaks (or any breaks for that matter), it’s usually not enough to discuss nerd stuff with my colleagues. Oh no, we have to take it up a notch, so naturally we play puzzle games while on our break. One of our all-time favorites is the daily New York Times (NYT) Spelling Bee https://www.nytimes.com/puzzles/spelling-bee https://www.nytimes.com/puzzles/spelling-bee . It’s a game with simple rules: Every day, you get presented with an assortment of 7 distinct letters, arranged in a honeycomb-like pattern (one letter in the middle, and 6 surrounding it). The goal of the game is to come up with as many words using the 7 letters, with some additional limitations: ...

For a long time, one of my favorite hobbies was gaming, and one of my favorite games was DotA 2. According to Steam, I’ve spent thousands of hours playing it - and whether alone or with friends, I always had a blast! The premise of the game is deceptively simple: Two teams of 5 players, each controlling a hero, need to defend their base (so-called Ancient), while at the same time trying to destroy the enemy base. That’s the basic idea - you now understand the game. But, given over a hundred heroes, items, play-styles, etc., DotA is actually extremely complex, and virtually no two games are the same. It’s easy to understand, but hard to master - kinda like chess. ...

An article I’ve written for ShiftMag about uv, a modern Python package and project manager that simplifies dependency management for AI engineers.

Back when I was learning about neural networks as function fitters, I wondered if it is possible to force them to behave in strange ways for certain input values, as hidden features or easter eggs, like in video games. Let me illustrate what I mean: Imagine having a neural network trained at the simple task of calculating $y = sin(x), for~x \in [-\pi, \pi]$ Since neural networks are nothing more than universal approximators Ian Goodfellow et al. Deep learning, 2016; www.deeplearningbook.org Ian Goodfellow et al. Deep learning, 2016; www.deeplearningbook.org this task should be a breeze, even for a simple architecture. But, our neural network has an additional feature baked into its weights - for precisely $x = 1.2345$ it will spit out a bogus value, like $y=4.2$, which does not make any sense for a sine wave! ...