Archive

For a change of pace, I'd like to do a bit of a dev log. Some time ago I participated in a game jam, and made this game – Of Mice and Bad Choices – a short puzzle game, where you place cheese around the maze to lure the mice

⚠️This is a made up example! In the real world settings, you MUST NEVER give access to sensitive information to a public facing LLM in the first place. Just don't. This extreme example was constructed to illustrate how smaller transformer models can be used for guardrails, not how

I thought we've already decided that giving back feedback after interviews is a good thing. People were talking about it a lot a few years back. Apparently it's still not a thing for quite a few companies out there. I have just gone through an interview

Well, alright, this title is clickbait-y. I wanted to talk a little about one thing I've noticed recently. This is essentially subtweeting on a bunch of people I see on different platforms, that seem to be preoccupied by LLMs (and huge models in general) and appear to claim

This post is essentially a repost of the twitter thread I did right after the jam, with very little editing. Itch.io game page: https://dlowl.itch.io/of-mice-and-bad-choices Github repo: https://github.com/d-lowl/of-mice-and-bad-choices I've recently participated in Siberian Game Jam (November 2023 edition) (itch game

... to actually do your next job? (The picture above is the illustration of different but adjacent tools doing different but adjacent things) I've been thinking lately about how much hard technical skills are actually transferable between different branches of software engineering. Out of a conversation with my friends

This is D. Lowl's personal site, a brand new site by D. Lowl that's just getting started. Things will be up and running here shortly, but you can subscribe in the meantime if you'd like to stay up to date and receive emails when