I've built Skub, a sliding puzzle game for the browser, based on a classic boardgame: Ricochet Robots.
It started as a challenge of trying to simplify the boardgame mechanics to fit on a mobile browser, which led to an 8x8 grid.
Since, it has evolved to a bit more of an experimentation with Deno, and a way for me to truly try out AI-assisted development. Claude Code has been especially helpful in building the BFS solver and setting up CI, less so in UI and logic.
I hope you enjoy it, all questions / feedback welcome.
it guessed great commands, but it formatted it always with a colon up front, like :help :browser :search :curl
It was trained on how terminals look, not what you actually type (you don't type the ":")
I have since updated my code in my agent tool to stop fighting against this intuition.
LLMs they learn what commands look like in documentation/artifacts, not what the human actually typed on the keyboard.
Seems so obvious. This is why you have to test your LLM and see how it naturally works, so you don't have to fight it with your system prompt.
This is Kimi K2.5 Btw.
https://philfung.github.io/openvaxx/
And this recent story about a man who worked with researchers to create a personalized cancer vaccine for his dog:
https://medicalxpress.com/news/2026-03-ai-cancer-vaccine-dog-oncologist.html
It got me wondering what the current technology, research, and startup landscape looks like for personalized mRNA medicine in humans.
Are any HN people working in this space, or close to it? I’m especially curious about: - how real the pipeline is today outside major institutions - which parts are getting cheaper or more accessible - which parts of the pipeline is being taken over by software and possibly new AI models - where the real bottlenecks are: sequencing, target selection, manufacturing, QC, regulation, or something else - whether anyone is building tools, infrastructure, or startups around more individualized mRNA therapies