Lumina has made a probiotic strain that is able to, theoretically, prevent cavities. I don't care that much about, but I do think it is a neat strain that can likely colonize your mouth. I'm genetically engineering it to express sfGFP, which would theoretically make my teeth fluorescent green under black light. Would be fun at raves! Also, if I make out with anyone, you could theoretically see changes in microbiome composition just from green-ness. I do wonder how much microbiomes are shared while kissing: this would be an example of a way to directly measure that, instead of just measuring on proxy like much microbiome research
Ask HN: What Are You Working On? (Nov 2025)
131–140 of 1001 posts
Re: Ask HN: What Are You Working On? (Nov 2025)
#132Re: Ask HN: What Are You Working On? (Nov 2025)
#133Re: Ask HN: What Are You Working On? (Nov 2025)
#134Currently working on a take on Pokémon GO + Pokémon Snap but for birding. The goal is to explore your neighborhood, find birds, take good photos of them all. Next month, I'll be doing an event to find a rare bird, excited to see how it goes! It's still a small closed alpha, if anyone is interested: https://testers.birdlego.com Here is a rough trailer of it: https://www.youtube.com/watch?v=yVpR8aafFjI
Re: Ask HN: What Are You Working On? (Nov 2025)
#135After a 2-minute voice conversation, Sage generates a personalized 6-module roadmap with build-first projects. It checks in by voice, analyzes your reflections, and regenerates your plan if needed. You can invite friends to your Support Squad for accountability.
The biggest insight so far is people don’t want “infinite content.” They want structure and someone who remembers them.
would love feedback!
Re: Ask HN: What Are You Working On? (Nov 2025)
#136Re: Ask HN: What Are You Working On? (Nov 2025)
#137But now with travel and visa guides to help remote workers become productive in Japan and South Korea ASAP and give them visa guidance if they want to stay a bit longer.
Re: Ask HN: What Are You Working On? (Nov 2025)
#138Re: Ask HN: What Are You Working On? (Nov 2025)
#139Re: Ask HN: What Are You Working On? (Nov 2025)
#140Because they're trained using imitation learning instead of RL, they're scalable and easy to deploy with your own data (also open-source!).
Mainly targeted at and tested on quickly disqualifying prospects in sales calls, but can be applied more broadly.