It's all trade-offs between price, speed and accuracy. It's no good using a free model when the latency is 10s+ and the throughput is sub 100token/s and this is often the case on OpenRouter. I have to use a speedy provider like Groq and a small model.
Dumber models need a lot more context to correct the inaccuracies. I'm mostly using mid tier models like Gemini 3 flash to generate the boards and then I use the fastest models to answer questions (currently gpt-oss-120b on Groq).
I've mostly been using it as a calendar interface and email drafter. I also find it useful for a daily agenda with meals, meeting, weather and so on. I find the responds slowly (10-15s) so I've probably configured it poorly. I'm just using a Hetzner node and OpenRouter but maybe local is better?
I think a big proportion of them wouldn't 'know'. At least in my experience considering selling out the partners or buyers will try to keep a good image. But there are smells. Maybe the partner has their HQ in place that is a hotspot for intelligence/security industry or the deal is at such a price that it would only make sense if the asset as purchased for nefarious purposes.
I too get worried when I see npm. Luckily I use bun install <everything> so it's all good. In seriousness I do at least have a 7d min age on the packages.
I add multiplayer to most of my puzzle games now because couples love it. Redactle is the main one. Often Redactle is too hard to beat alone but it's great for a colab.
reply