I'm going to hazard a speculative answer with poor evidence: love.
The ants love one another, as shown by their child-rearing, grooming, playing, the "antennating" mentioned in the article, collective defense, and deliberate handling of their dead.
We don't understand their language, but I have a certain faith that ants experience a very similar kinship for their sisters as we. If they were strictly-rational robots then why would they show these behaviors?
Super nostalgic for me just to see the name. My computing teacher gave me a Knoppix LiveCD when I was about 18 and I immediately fell in love with Linux. Within weeks I was (repeatedly) attempting to install Gentoo on my first computer that I built. What a wonderful project!
Oh man, good on you identifying a product that needs to exist. I've used a few TikZ editors (both online and desktop) and none of them are just amazing.
But, I've taken my papers to Typst. Could you have the agent do the same thing for Cetz, the TikZ equivalent for Typst?
Not OP, but I can comment on my anecdotal experience switching.
Typst is great. I had been using Markdown with Pandoc to write a book. I frequently needed to use raw LaTeX commands, and it was mostly OK but I had a few frustrations with my setup. The biggest was time — my Makefile process was taking several (like 10+) seconds to render everything and that was really tedious when I was trying to get TikZ drawings perfect. My other frustrations were floating figures never appearing where I wanted (common complaint, I think) and weird font issues with certain math symbols in code. (I settled on JuliaMono, which was OK but the experience wasn't a happy memory.)
Maybe six months ago I decided to try Typst. I went through the tutorials and made something basic the same day. Got comfortable and eventually pasted my entire book into Typst and started the tedious process of finding and replacing until it compiled. I still occasionally find a \times or something that I missed.
Unlearning backslashes was the hardest thing for me.
The next hardest thing was switching from TikZ to Cetz. Cetz is pretty good, but just like TikZ it takes an investment to learn. I tried to have AI translate my figures and it was not very successful. Someone wrote a webapp that can translate Typst to LaTeX and the reverse. It is a good way to get started on changing figures, but you'll have to clean up its output by hand a lot.
Though I used LUA LaTeX, I never did find any uses for its scripting. With Typst, I use it all the time. Functions are really easy to write. I recently wrote a REPL formatter to show inputs and outputs in code. I'm happy with it and ought to publish it. My only complaint is that all functions are pure functions; there is not a way (that I know of) to share state from one function invocation to the next.
The templates on the Typst universe are pretty OK, but we need more. I will have to change some of the formatting decisions in the book template I'm using.
One thing I've encountered that I could do in LaTeX that I can't (easily) do in Typst is labels on a NiceMatrix. Otherwise, I've felt like I could do everything in Typst that I needed from LaTeX.
Not OP, but thank you for your sharing this. If you don't mind a follow-on question, I always hear people talk about the "runtime" in languages like Go and libraries like Tokio. What is that these runtimes are doing that you cannot get from the likes of libc and these Windows DLLs?
The header of an IPv4 packet has the source and destination addresses, both as 32-bit values. These fields are adjacent, and there's other stuff next to them. If you appended more bytes to the source address, routers would think that those new bytes are the destination address. This would not be backward compatible.
Interestingly, what you're describing really is similar to how many languages represent an IPv4 address internally. Go embeds IPv4 addresses inside of IPv6 structs as ::ffff:{IPv4 address}: https://cs.opensource.google/go/go/+/go1.26.2:src/net/ip.go;...
For what it's worth — my last workplace did not allow cell phones in the building and I learned to love it. When people attended meetings, we all made eye contact and talked about the task at hand. Nobody ever got distracted by notifications or tuned out with boredom. And since we all had traditional telephones at our desks, someone would come get you if your family was calling with for an urgent crisis. I miss it.
My kids' school banned phones during the school day. The principal promised that the office would relay any messages if parents call, and they do. I would be interested to see if there are already statistics showing academic success. That is, are grades and test scores affected by phone bans? The article talks about graduation rates, but doesn't directly address grades and scores.
I remember a colleague jumping through hoops trying to get Python installed on an enterprise computer. We never did get to a yes and resorted to using PowerShell instead. The policy constraints at enterprises that this author describes are very real and very harmful.
Perhaps the wildest thing to me is how you'll have senior leaders in a company talking about innovation, but their middle managers actively undermine change out of fear of liability. So many enterprise IT employees are really just trying to avoid punishment that their organization cannot try new things without substantial top-down efforts to accept risk.
Cool! I just recently began learning the Raspberry Pi Pico. Could anyone recommend a specific display that I could use with the Pico 2/2W and Mousefood?
Similarly: "The indication for machine-generated text isn't symbolic. It's structural." I always liked this writing device, but I've seen people label it artificial.
YouTube is actually one of my very first places to go for new concepts. For example, one of the recent Advent of Code puzzles was solvable with "coordinate compression," a technique I had never heard of before. I didn't find much, and what I did find wasn't an especially high-quality presentation, but it did teach me a magical new concept that helped me to finish the puzzle.
I have also benefited so much from MIT OCW lectures. The quality of their teaching is so high that it showed me that when my children go to college, it will be worth it to send them to a much more expensive elite school.
Sports. CrossFit and similar social sports have been healthy for me and for many others, and I think the community is at least equal to the exercise in improving people's lives.
Not saying this is the only way, but it made a big difference for me and my friends. I realize the physical challenges are artificial, but so is an Advent of Code puzzle when you already have a day job. Hard things are worth doing because they're hard, and they're even better when done together with those you love.
This is not the first article I've seen where developers say they're getting overwhelmed by AI-generated bug reports. Maybe this is a new way people can volunteer to help open source.
If anyone is struggling to triage bug reports in a Rust open source project, please contact me and I will see if this is something I can donate some recurring time to.
The ants love one another, as shown by their child-rearing, grooming, playing, the "antennating" mentioned in the article, collective defense, and deliberate handling of their dead.
We don't understand their language, but I have a certain faith that ants experience a very similar kinship for their sisters as we. If they were strictly-rational robots then why would they show these behaviors?