It’s March 2026, and the last 6 months of AI progress have been really exciting to watch. In particular, the models are continuing to improve at an impressive rate. I don’t watch leaderboards carefully, and I don’t know whether the pace actually measures up to the boldest claims from 2024, but in my everyday use and code gen work, the improvement feels palpable.
The 2026 Winter Olympics came and went in a flash. I tuned in for as many of the performances by American competitors as I could, and despite early stumbles, there’s a lot that the American team has to be proud of. I’m not overtly patriotic, but I appreciate that the realm of international sports is one place where a feeling like national pride can still take hold, unencumbered by political or ideological caveats....
It’s May 2025, and the AI revolution is in full swing. If you’re a knowledge worker and you haven’t integrated AI into your workflow somehow, then… like, what are you doing? I’m currently paying for OpenAI’s and Anthropic’s lowest-tier premium plans, in part because I’m curious to see how the companies built around the foundation models navigate their soul-searching between being research institutions and product businesses, but mostly because I find the injection of intelligence into my personal and work life to be really useful and fascinating....
I’ve wanted to record some casual reflections on my experience learning and getting better at Mandarin Chinese, particulary as someone whose productive language skills (namely, speaking) far outpace the receptive skills (listening). When learning a language, there’s a point when your command of it reaches an operational level, such that you can make your way through casual, day-to-day conversations. While graduating to this range of proficiency represents a significant milestone on the path towards mastery of the language, it also brings a new challenge: you can no longer have high confidence about exactly how much you understand of what is being said....
My initial reaction to the term prompt engineering was skepticism that anything of the sort could be called engineering. Having now spent a bit of time using LLM AI to produce a solution to a small content generation problem, I’ve arrived at a few takeaways, some of which have pushed me to be less dismissive of this notion. ...