Live data from Hacker News

Ask HN: What are you working on? (January 2026)

news.ycombinator.com

821–830 of 914 posts

Re: Ask HN: What are you working on? (January 2026)

#821
I am building a Claude code orchestration tool that automatically updates agent skills based on ambiguities flagged in agent responses by a meta overseer. The overseer reasons on top of the worker agents’ reasoning. When that happens, it sends me async requests and early on there are a lot of them. Based on my input, the system updates skills or splits them into smaller ones for tighter context control. This sets up a HITL driven training loop that constantly refreshes skills and adapts the agent swarm to new tasks.

I think of it as recursive transfer of human expertise into skills.

I know this is vague and probably raises more questions than it answers. I will share more once it reaches a semi autonomous working state.

Re: Ask HN: What are you working on? (January 2026)

#822
post #148

Earlier quoted context omitted.

I really need to do a write-up. I kinda just whip up the easiest path and do it. For example for the grape, I needed to knock out some tryptophan synthesis genes so I could redirect the bioflux. Problem is that in bakers yeast they have a whole buncha copies of their chromosomes, so I had to knock out one of the genes and replace it with a different gene from grapes. Did that with a quick lil CRISPR switch. Had to el…

How much expensive lab equipment do you need to do something like this? "A quick lil CRISPR switch" sounds like "oh just my homemade fusion reactor hooked up to my kitchen warp drive" to me, yet you make it sound so simple!

Eh, other than the electroporator I could probably do it for about $100-$200 bucks of equipment if I had a decent kitchen.

Reagents probably about $300, but you can use em in a bunch of reactions, in aggregate down to like $50.

The fundamentals of biology are really cheap, but the skills to actually do it are really expensive. It’s way more manual than you imagine - like how my thumb moves. The equipment is way more fundamentally basic than you imagine: the only thing you can’t 3d print and build from off-the-shelf stuff is the instant pot I use for media prep

Re: Ask HN: What are you working on? (January 2026)

#823
post #148

Earlier quoted context omitted.

I really need to do a write-up. I kinda just whip up the easiest path and do it. For example for the grape, I needed to knock out some tryptophan synthesis genes so I could redirect the bioflux. Problem is that in bakers yeast they have a whole buncha copies of their chromosomes, so I had to knock out one of the genes and replace it with a different gene from grapes. Did that with a quick lil CRISPR switch. Had to el…

Starting from nothing, how much time (and money) might it take an individual to learn how to be able to do these things?

I’d recommend buying an Odin kit and just trying it. Doesn’t take THAT much to get into genetic engineering.

The tough part is mostly the finesse in the simple things, like trying this in bakers yeast rather than lab yeast, or the genetic design.

Cost is quite high for mistakes, but LLMs are honestly quite good to help you out with the basics. You MUST at least try to read the papers though - it’s not like coding where you can mostly let it do its thing.

Re: Ask HN: What are you working on? (January 2026)

#824
post #148

Earlier quoted context omitted.

I really need to do a write-up. I kinda just whip up the easiest path and do it. For example for the grape, I needed to knock out some tryptophan synthesis genes so I could redirect the bioflux. Problem is that in bakers yeast they have a whole buncha copies of their chromosomes, so I had to knock out one of the genes and replace it with a different gene from grapes. Did that with a quick lil CRISPR switch. Had to el…

Curious why you do CRISPR when HR works great in yeast. If you are having trouble transforming, try spheroplasty.

Already answered there: I’m using bakers yeast, not lab yeast (store-bought S cerevisiae). It’s not haploid, often it’s tetraploid. HR doesn’t guarantee homozygous transformation.

Same answer for electroporation vs spheroplasty. I’ve found with wild yeasts or less tamed yeasts (pichia), sometimes just nuking the damn thing with kV will just work, whereas those chemical methods can be way more finicky. Time is money

Re: Ask HN: What are you working on? (January 2026)

#825
post #238

I'm working on Tech Posts ( https://techposts.eu ), a Hacker News for Europe! Since the last time I posted on HN it's gained a decent amount of traffic and users. I'm particularly happy with the jobs section, which is growing into a high signal-noise source for European tech jobs: https://techposts.eu/jobs The reason I started this website is because so much incredible innovation and growth in Europe flies under the…

I've also bookmarked it! Great idea Hi from a Portuguese living in Copenhagen

Re: Ask HN: What are you working on? (January 2026)

#826
post #118

I’m genetically engineering yeasts to make subtly flavored breads. I’ve already done grape aroma, now working on wintergreen. Also working on a red chamomile (using beat red biosynthesis). Just for fun. Red chamomile tea! The idea is to have niche invite-only genetically engineered flavors that I can bring to parties around SF :) what’s more special than a genetically engineered organism that you can ONLY get if I’m…

Loosely related: my new hobby project is growing and nuturing sourdough that's optimized for gluten free bread, and I'm cultivating a couple of different kinds to find out which taste I like the most. It kind of escalated a bit once I realized that different mixtures of bacteria cultures produce differently tasting dough/bread and that you can strengthen the grow rate by optimizing the external variables.

Very neat! How do you standardize the gluten free mixes?

I’ve been thinking about trying this since my mom is gluten free

Re: Ask HN: What are you working on? (January 2026)

#827

Still an AI time tracker that watches your screen. Currently experimenting with a proactive agent, Don, that pops up like clippy and also works over email. https://donethat.ai All the data security measures here: https://donethat.ai/data And other tools out there: https://donethat.ai/compare

Hmmmm. I am not sure I would feel comfortable running this.

Totally understand that. I’m trying everything I can to make it as secure and private as possible, see https://donethat.ai/data but can never be 100% of course. At the /compare link I list some open source tools that try to do something similar fully local.

Re: Ask HN: What are you working on? (January 2026)

#829

I bought a 300 litre aquarium about 6 weeks ago for the living room. Added soil, plants and water. Have spent the last 6 weeks watching plants grow, and snails that smuggled in on plants, multiply. I over fertilised it and left the light on accidentally for a couple of days whilst I was away and experienced an algae bloom, which was interesting. Added some cardinal tetras and amano shrimp yesterday and have spent a l…

Oh man... you just throwback thursdayed me to my last weeks thought. I really want to get a pet fish, like a betta for my mental health. I feel like it would motivate me when im working on projects to have a buddy near me. Is cleaning the tank a lot of work? Agh!

The main work is doing a water change, which I think I'll have to do every couple of weeks going forwards, but we'll see. I had to do it more often at the start whilst the tank was cycling. Takes me about 40 minutes. I also have to trim the plants every so often. Oh, and feed them of course. It doesn't feel like a lot of work or a chore to me atm.

Re: Ask HN: What are you working on? (January 2026)

#830
post #758

Earlier quoted context omitted.

> how I wish I was paid to work on this type of problems Did you apply for funding? Any subsidies?

When the code is ready to be opened and I have settled for a design; right now it's very much in flux and I want to see where the vision takes me, and which challenges I encounter along the way. I'd like to apply for funding by the end of this year, when I'll have saved enough money from contracting to dedicate myself fully to this project.

From my experience I never felt "ready enough" to apply. I also underestimated, despite knowing how slow the process would be, the time required not to submit a proposal for funding but how long it would take to receive an answer. Consequently I recommend you start "too early".
Post reply on HN