tito

200+ comments tripping over themselves to say “I’m not bothered” and zero github repos to process 500 page datasets. HN letting me down!

Anyone vibe code a tool to read the data? I wanna see what mine is!

OK sounds good!

I wanted to understand how well this process works for a topic I already know.

I made for carbon dioxide removal, which I work on. First shot had most of the visualizations well made. And it was nice to see what I work on in a visual way that I hadn't seen before. I added labels to the warming graph and a removal build out graph too: https://removal-valley.netlify.app (while I saw familiar inputs as the sources, I didn't go through to make sure the numbers are all tied in properly, so that's where I would recommend someone proceed with this draft. But the things that are visualized, and how they're visualized, that's good to go)

I also had it animate the history of focused research organizations (a topic I was looking to learn about). That one is more a history of the space, and after that ends it's a simulation: https://fro-park.netlify.app

All three of these started with the prompts given in the OP and put into Claude. I haven't reviewed the actual numbers underpinning the models yet (nothing jumped out at me though as terribly wrong) so I included a "Draft" tag at the top of the page.

Code for both is on my GitHub: https://github.com/titojankowski/removal-valley https://github.com/titojankowski/fro-park

And I love your question, I really want individuals to be able to take clear action on this. We've built tools for that, clearly we're not there yet (higher CO2 emissions than ever last year) but not yet "plug this thing in at home".

The other thing that comes to mind is we have a online course where thousands of people have got together and learned about how carbon dioxide removal works: https://bootup.airminers.com/

It's book club style, so you're matched up with a bunch of people and you get to talk through the topics together. Let me know let you think about all this!

There's different flavors of carbon dioxide removal hardware, though they're mostly industrial scale.

You can pay to suck carbon dioxide from the sky. Here's one example using this vacuum machine by Sirona: https://www.sirona.tech/remove-co2#Individuals

(I recommend removing 1 kg just for the experience, it's $1)

In terms of buying the hardware yourself, the low end is still tens of thousands of dollars. If you happen to own a farm, a pyrolysis machine can turn your farm waste into solid carbon that's locked up for hundreds of years. And people will pay you to do it too.

If you like investing, you can invest in these companies: https://airminers.com/invest

I ran this on ship tracks to see the global warming result. It built a toy climate model for cloud forcing: https://ship-tracks-tycoon.netlify.app

For background, in 2020 the International Maritime Organization changed fuel standards globally. The intent was to reduce pollution, which is great for human health. But, it turns out some of that pollution was supporting cloud formation and creating a cooling layer globally. And temperatures started to climb when the pollution was removed.

I haven't looked through how it's doing the calculations yet but this kind of visualization is full of possibilities if done right.

Thanks for making this guide!

Here's the code and publications/sources on Github for anyone to poke through: https://github.com/titojankowski/ship-tracks-tycoon

And since the details of ship tracks are a newer topic for me, I'm curious about Gell-Mann Amnesia. Next I'm going to apply this to a topic I understand well and will report back. Stay tuned! (will be tomorrow, bookmark or reply to this thread)

hey thank you for the shout out!

Working on reversing climate change. Carbon dioxide removal.

Also getting curious about mechanisms to prevent damage from high temperatures in the short term. There's a project over the Great Barrier Reef I've been digging into what mechanisms they're using: https://barrierreef.org/news/explainers/what-is-cloud-bright...

$60,000 for car with sensors? I'm delighted to hear Waymo may be anticipating such low price points: "We are hearing that Waymo is close to having its entire package (car + Waymo sensor suite and driver) at around $60,000"

If it was circa 2010 I think I remember those guys. It was partly for people who wanted fresh algae smoothies? How big a tank do you need to remove 1 kg of CO2 per day…

Agreed! My point is that it’s possible financially, but yes the incentives are messy.

I find it especially a problem at night. Started out leaving the window open in the bedroom, but that lets in noise and wind. Current solution is leave the bedroom door open and have a window cracked open in another room. It seems to work out really well as measured by my CO2 monitor.

I mentioned this elsewhere here, but a friend told me that it’s not only CO2 that leads to that mental fog, but it’s also the VOCs in the air too. All that gets cleared out by having an open window.

Same here, I wonder if there’s some missing conversation in the hacker news community about climate. Seems like some people really wanna talk about it even off topic.

I get to spend plenty of time working on climate already, so I was particularly interested in the indoor air pieces. Someone below suggested there’s a ventilation system alternative. I wonder what you could do with a little miniaturized direct air capture machine. Probably crazy energy inefficient and whatnot, but maybe a cool experiment.

During World War II, the United States spent 40% of its GDP on the war. So we can spend big on things when we decide to.

That would be the equivalent of $12 trillion per year today, and we would clean up the climate in a jiffy with that. It would be a huge opportunity for job creation, manufacturing, innovation. It’s wild as a society we’ve convinced ourselves that stabilizing the climate is a cost instead of a massive opportunity.

As somebody who works on carbon dioxide removal at planetary scale, I was excited about your article about indoor air… but nearly every comment here seems to want to talk about the changing climate!

That’s cool. Is that something that you’ve built or installed?

Even if that is a better solution, I am personally curious about an indoor carbon dioxide zapper, since what I work on is carbon dioxide removal at planetary scale.

Just popping in here to say that the IPCC has no model for a stable climate that doesn’t involve removing many billion tons of carbon dioxide alongside complete decarbonization, so unfortunately simply stopping emissions at this point isn’t enough. Some level of carbon dioxide removal is required to maintain a stable climate.

Hi! I work a lot with carbon dioxide removal systems. If every person on Earth dropped everything and started making biochar, it would definitely make a huge difference. Yes, we add a lot of carbon dioxide to the air of a year, but it’s doable to remove it. Humanity has taken on much bigger challenges before and succeeded. Now that’s not to say that it’s likely. I think it’s entirely unlikely that we avert the worst impacts of climate change unless something big changes. Thankfully, we get to choose what to work on every day, and I get to choose to work on that alongside inspiring people. (and yes, this isn’t what the article is about, but it seems like it’s what everyone is responding to)

I’ve always wanted to jam on how to create an indoor carbon dioxide removal system. (I think that’s what this article is about but perhaps it’s indirectly about the changing climate)

1 kg per day of material adds up fast but that assumes zero ventilation. If I simply wanted a system to keep my office below 500 ppm all day, I wonder how much material that would produce.

Anyone ever build a little carbon dioxide zapping system for indoor air quality? I’ve also heard that indoor CO2 isn’t actually all that bad but it’s VOCs that are what make me feel sluggish.

Built while waiting for Claude sessions to return to reliable.

What processor in the MBP?

Update - now running at 4 tokens / minute https://github.com/gavamedia/deltafin

“How long?” he said. “Seven and a half million years,” said Deep Thought.

thanks!

I read about its format being tough to compress further. What should we expect in terms of creating smaller models to run locally?

lovely! I'm a fan of asynchronous LLM systems like this. There are times where I prefer slow, complete responses to immediate replies.

For example there's a billboard on 101 for Poppy Bank offering 4% interest and I asked my daily LLM to look into it through a voice note. The next morning, lo and behold it says it's an advertised rate, hard to actually get, and businesses aren't eligible. OK, done. Better than getting the response while I'm driving. And even if I wasn't driving, there's a level of, how do you say, it's easy to drop it the next day when I see it vs getting engrossed in the research.

Oh, is that how it works? So, when somebody says a model is running at X tokens per second, it means that the thinking process is running at that, and output tokens are much lower then? Thanks to the explanation.

Are there any well thought through stories about what this would look like? For example, I'm thinking about like nutrient flow, decision making, energy input, gravitational force, things like that seem to govern the value and speed of intelligence.

Done, Mac -> Max