agentultra

Or it’s a fabrication of some kind. Some times people lie to make themselves look good. Or the omit important details.

So is honey? And red food colouring used in a ton of products is made out of beetles or something. We eat bugs and bug stuff.

Something like this for me. I was on an Amiga. Later “downgraded,” to Intel PCs. But by that point i was already hooked.

BBSs were how I learned everything because there wasn’t really anybody near me in my little rural area of the world that had a computer let alone knew how to program them. Internet wasn’t public yet, just getting out of the lab.

What I grew up in was the counter-cultural era of tech. Distrust of authority. Freedom of expression. Queer. Weird. Against the War on Drugs, neoliberalism, police, all that.

Demos were huge. Scrolls were also huge. Mods were huge. Good times. When I think of back then I still hold out hope for today.

Truth. And a shame. True piece of art. Doesn’t deserve to be locked down like it is.

People are also concerned about those losses of forest too. And they do make the news. The rapid increase in rainforest loss in Brazil is often in the news.

Loss of forests affects us all. And they’re not as renewable as people think.

Not wholly. It’s under study. I don’t mean in the sense that you can’t read words anymore. I mean in the sense that comprehension and attention go down.

Every time you don’t write the script you lose a little of the ability to do so.

Just like if you don’t read you will lose the ability to.

These skills are not innate to us and can be forgotten over time.

I wonder if it will get to the point where people don’t even know what to ask for. Or how to judge if what the machine produces could have been better. Or if it does what they think it does.

They exceed us in a sense. They can generate the kind of proofs that a computer scientist could love: it doesn’t matter how elaborate, long, or obtuse the proof is as long as the checker says it holds. Many proofs that people consider elegant and have expanded human knowledge tend to have qualities designed with intent for an audience to communicate the idea, motivation, and result. They exceed us in the sense that Alpha Go exceeds most players of the game.

These planets are also so damn far away that we’d never hear from any ship we could possibly send out there again. Even if we could send information at the speed of light. It would be pointless.

Given that after arriving everyone could just die from some weird protein floating around in the air and you might want to look before you spend the entirety of our economic efforts reaching it… erm, look before you leap.

You can probably still find the leaked code online. It’s not exactly a bastion of software engineering. Plenty of folks have reviewed it deeply.

Maybe. I’m not certain the pages and pages of informal markdown specifications for the agents really add anything for me.

Knowing what your software does is such a hard problem. Most developers have an idea but if you ask, how are you sure?, the answers reveal how little they know.

Most often we’re satisfied with signals and indicators that it works and we build theories and mental models that use to try to avoid the effort of proving anything.

Worse is what happens when you start using LLM models to generate the code for you. I find you start losing the mental model short-cuts; you start to trick yourself into understanding the code. You understand little.

And what few studies there are of code review suggest that we have very little impact on code quality after reading more than a couple hundred lines of code over an hour.

So the current mental leap is, “the AI is a better programmer than I am.”

I think it’s still worth becoming a better programmer regardless. And there’s no royal road. You just have to write code and struggle with writing bad code.

If you want to create a programming language, create one. Do it because you enjoy it and because you have to answer a burning question. Learn how to formalize a language. Decide on whether to do that with operational or denotational semantics. Understand IR, optimization pipelines, and all that. Every moment spent on acquiring this knowledge is not lost and the time is not wasted. You’re enriched by it!

There are other people out there doing the same thing. Share with them. They’re more than happy to find like minded people.

Choosing to give up is not the answer. Claiming that engineering is, “solved,” is promoting a false narrative. It’s almost nihilist. Defeatist at least. Don’t even admit it or repeat it. It’s just not true.

All of the crypto bros told us how inevitable their technology was. We didn’t have to argue. Their constant chirping just got annoying and now look. They’re basically gone having exhausted the well.

A lot of LLM technology is in the same boat. You have a bunch of noisy people lying and hyping up the technology to line their pockets. History will sort them out too. You don’t have to give bad arguments space.

I think the worst effect AI has had on our industry is this malaise that has settled in and convinced so many people to give up, stop contributing, and accept the future that the hype bros have made up. They’re the ones getting rid of jobs, telling everyone they’re gonna get replaced, that there’s no need to learn programming or how to do software engineering.

Software engineering is going to be more important than ever. Despite the astonished claims of the intermediate beginners that Claude one-shotted the app they couldn’t be bothered to learn how to build for six years… it doesn’t magically generate good software. It can do a lot but at the end of the day it still needs a human operator to understand its output and direct the harnesses.

The thing to watch out for is people giving up on engineering as a profession. Software has barely entered that arena. But if we start vibe coding air traffic control software, it’s probably time to stop flying.

The point of software engineering hasn’t been to generate code. It’s to understand what the heck we are building. To develop the processes, techniques, wisdom, and knowledge to direct the work. To bounce between theory and application and back again. To better ourselves and make computers do useful things.