iamwil

But then, how do you keep the theory in your own mind enough to steer the agents to extend the program? I've been asking around, and different people seem to have different ways, colored by the way they work.

How do you coordinate their work? Do you just have one orchestrator/mayor that you talk to, and it coordinates the rest, and the rest talk amongst themselves? How do you ensure they're doing the right thing or efficiently?

How, if at all, do you keep the architecture or a working theory of the code in your head?

This is kind of a cool concept. It's like Space Golfing.

Another alternative is to make it like a turn-based Scorched Earth (Mother of all games), where you can either

1. launch asteroid size projectiles across star systems in a field of stars and black holes to it each other.

2. launch projectiles that then place black holes (perhaps either by timeout or signal--taking into account the speed of light!) to change the field.

It's a good start!

Hrm, I don't think so with a cursory search on NewGrounds. I can't remember the name.

How often you have to take algorithmic complexity into account depends on what level of the stack you're at, but even at the application level, I think understanding algorithmic complexity is still important.

I was working at Company X around 2013, and we had a Rails ecommerce site. Trivial in the algorithmic sense. Had a contractor that pushed a change that somehow made everything crawl. When we did profiling together, it turned out he had written an O(n^2) algorithm when looking up country codes or something. Sometimes, there's no off-the-shelf library, and it's the minimum a dev should know not to do.

I'm not saying it should be a maniacal focus, but it should be taken into account. Of course, it's with judgement. We get shittier and shittier software if it's not taken into account at all.

I remember playing a crap web game in college, kinda like gunslinger, where you try to shoot people who turn around with a gun (and not those without). When I graduated college, Ian--one of my good friends at work--ended up being one of those guys in the game! Turns out that game I was playing was built by Tom Fulp, and he was using his friends (like Ian) as characters in his games pre-Newgrounds. All that messing around with crap games on the internet paid off. He had started Newgrounds while in college, and had quit to do it.

Met Tom once, and he was a cool guy, but he didn't believe in the stuff that they taught in CS. He had a long rant about how learning string diff algorithms were useless. Anyway, it turns out later on, he went back to college to finish his degree. When his classmate(s) found out who he was, this one kid was so excited to sit next to him. "Do you know who he is?!" he would exclaim to his professor, to Tom's embarrassment. I wonder if he had to do string diff algos when he went back to finish college.

Working on an interactive explainer for code. When agents write most of the code, I find I'm losing the working theory of the code/architecture. Code review had typically served a couple of purposes, two of which are catching errors and disseminating codebase knowledge amongst the team. I find that adversarial agent reviews are good at catching errors, and that I prefer to learn about the architecture before/while I'm designing the next feature, rather than after.

I've also been designing a APL/BQN-like language that uses Korean as a way to compact and compose the meanings of the operations.

Plato thought writing was a lie:

> If men learn this, it will implant forgetfulness in their souls; they will cease to exercise memory because they rely on that which is written...And it is no true wisdom that you offer your disciples, but only its semblance, for by telling them of many things without teaching them you will make them seem to know much, while for the most part they know nothing, and as men filled, not with wisdom, but with the conceit of wisdom, they will be a burden to their fellows.

Basically, reading writing (without instruction) will only make people seem like they know stuff, by parroting others, when in fact, they know not much of anything.

Any specific Sony bots you're recommend looking at and studying?

This reminds me a web 2.0 startup in 2006. It was similar in that it wanted people to break down arguments into a flowchart. Had more of a public collaboration flavor to it at the time.

https://web.archive.org/web/20060427152801/http://www.standp...

Though I like this angle a bit better, it'd be interesting to look into why standpoint had a hard time.

That's great. I spent the majority of my time at the Recurse Center doing a first implementation. The full rebuild version of an insert is trivial. The incremental version took most of the time.

This is pretty neat. How long did it take for you to implement the core basics?

Upon insertion do you incrementally build the tree, or do you rebuild it from scratch?

How did you ensure the distribution of nodes was about the same with the chunker?

Not for me. By asking it to interview me, and then working through the options and their consequences, it feels more like the whiteboarding-with-a-colleague part of engineering. I don't have to remember to specify everything. The agent asks me things that it's unsure about, still ambiguous, or open questions. I have it write down all the decisions we made.

The resulting decisions are fed into the coding loop with guardrails derived from those decisions. The agent one-shots features once it goes into the coding loop.

btw, your website is down.

Has there been a time when your spec was accurate, the agent implemented it, everything passed — but you still felt you didn't really understand what was happening? If so, what did you do about it? Did it degrade your ability to make subsequent specs?

> when you come back later and have to remember wtf is going on."

When that happens, do you read just the spec, or do you also need to read the code? Is there a difference between "I can remember what I intended" and "I can predict what the system will do in a situation the spec didn't cover"?

Interestingly, you said the spec author must be you. What happens when you join a codebase where someone else wrote the SPEC, or where an agent wrote the code and nobody spec'd it? Is the spec still sufficient, or does the "you must write it" part mean the understanding doesn't transfer?

I think the cringiest are people talking about their cancer or their divorce, and how it helped them realize an insight about B2B sales.

Was "Self‐Portrait as a Drowned Man" thought of as great art at the time it was taken in 1840? Or was its status as great art a retroactive judgement with the perspective of time by people after 1840?

Not being familiar with the piece, so I looked it up. Seems like it was a protest correspondence aimed at a specific institution, not a public artwork. It doesn't appear to have been exhibited, reviewed, or discussed in print in 1840. Mostly circulated privately.

So I don't think it's a good test. Because you're asking me to point out an equivalent piece in the billions of generative art produced in these six years that would be judged by future historians to have great artistic value. If we were both back in 1840, we both wouldn't be able to point out "Self‐Portrait as a Drowned Man" either. It never posed itself as art at the time, and we'd have to know what future art historians thought.

Yes, I stand by the "lacking perspective" comment, because your judgements on photography and what's considered art are from the current modern point of view, rather than putting yourself in the shoes of those judging photography when it first came out--which is the shoes we find ourselves wearing when it comes to judging generative images, because the alternative (retrospectively judging it from the future) is unavailable to us.

Hence, my core argument still stands. In what way is photography different than generated images, where in photography is considered art because humans can exercise their creative judgement, but in generative images isn't because humans cannot exercise their creative judgement?

To argue against my own stance, the tact you should have taken could have been:

If one major component of art is the human judgement, how could humans could be credited for exercising any judgement at all when prompting, when LLMs are at the end of the pipe? And if they're at all intelligence, what's to say they're not superseding our intentions with their own?

Would you be able to pick out an example of "good photography as art" in the first 6 years of photography's existence, given generative media has been around for about 6 years?

Does the lack of an existence proof for fine art photography in the first six years mean that photography will never be fine art? Obviously not for us living in the future.

You'll need to propose a different, more honest test.

Your quick take lacks perspective. Photography wasn't always viewed to be art. Critics called photography "slop" in its infancy for a long while. See Charles Baudelaire for his 1800's take on photography:

> As the photographic industry was the refuge of every would-be painter, every painter too ill-endowed or too lazy to complete his studies, this universal infatuation bore not only the mark of a blindness, an imbecility, but had also the air of a vengeance. I do not believe, or at least I do not wish to believe, in the absolute success of such a brutish conspiracy, in which, as in all others, one finds both fools and knaves; but I am convinced that the ill-applied developments of photography, like all other purely material developments of progress, have contrib­uted much to the impoverishment of the French artistic genius, which is already so scarce.

Harsh. It wasn't a fringe view either. I encourage you to read how much creatives despised photography.

This argument was transferred to film when it first came out as well. It took a long while and a couple court cases before it was accepted that it took editorial choice for a photograph and film to be good. When it was accepted that to be the case, despite the aspects of mechanical reproduction, it was also accepted into the pantheon of fine art.

So it will be for AI generated images and video. So far, I've seen nothing inherent in the properties of AI generated media as a medium that obviates a human editorial eye. Even if AI could exercise comparable judgement, we will like an image because we want the curation of a specific person.

In Grant Sanderson's interview with Dwarkesh Patel about the future role of mathematicians (36:25), he says:

> One interesting take that I've heard about what mathematicians will end up being is that it's actually more analogous to art museum curators than anything else. The AI solved the thing, so the art exists. They even know how to explain it really well. But you still want someone to help you navigate this nearly infinite space of what ideas are worth engaging with. Even if AIs were in some sense better at that, I think we would always still prefer a human that we had a relationship with, because the way we get motivated to be interested in things is a social phenomenon. If you have some specific technology you're trying to build, that might be different. But the people listening to this podcast trust your curation on what's an interesting topic in the first place. It's not that they're landing here because whatever your next topic is, that's what they wanted to understand in a prior sense. They're trusting you as a curator. So my role, and arguably that of other mathematicians, might actually just shift subtly into that curation direction of what ideas are worth pursuing. That's a lot of my job right now.

Hence, I think there will be a role for AI generated images and video to be elevated into the fine art in the next couple of decades, and we'll see them in museums and exhibitions--as well more mundane uses like what's sitting on your phone right now--just like how photographs are used today.

Charles Baudelaire argued photography could not be considered a fine art because it merely produced mechanical replicas of reality without input from human imagination. He called photography "art's most mortal enemy" and the "refuge of all failed painters" who lacked artistic talent and training.

And if he's to be believed in 1859, photography isn't art.

But today, it's widely accepted that it is. And in all likelihood, you think it is too.

Why is that? And if you have an answer, you'd have to argue why AI generated images wouldn't follow the same trajectory.

Exactly my point. People simply weren't alive in the beginning of a medium, so they think how it is now is how it was always so. For the first 20 to 30 years of film, people disregarded it as art.

And somehow, it's a leap of logic that just because the AI image is generated that the text is also. It's as silly as asserting because someone used a camera, they hired a ghostwriter.

Would photography discourage OP from reading a blog? Should I hand-paint my imagery? If I am the type of person that would use a camera, then maybe I'd be the type of person to hire a ghostwriter.

What should an ESP32 with a display cost? It seems like the chip itself is a couple bucks, but the combo of ESP32 + display is around $40. Is there a way to do it cheaper? Put it together myself?

Is it a real physical cartridge? How do you get the source code off the cartridge at the end? Or does it give you a passcode to a git repo or…like an NFT with access to the source?

Other people have expressed interest too. Will let you know when I'm done.

It's not building itself, though I did build a harness. It's a collaborative workspace for humans and AI.

What I really want, is a plane that can load passengers like containers--or like a rollercoaster car. Of course, it should be comfortable. I just mean that the passenger compartment should be modular. So you can put your luggage in and get settled while sitting in the airport, and then when the plane comes in, it just side-loads everyone all at once. Once landed, it just slides everyone off, and you can just

I know that the crew uses the typical seating time to refuel and load luggage in the underbelly, but one can dream of not having to wait to get off the airplane.

I've been building and running my software factory for 8 months now. Granted, there's no automated pulling down tasks and pushing PR right now (soon!). But after specifying what I want, it mostly goes to shipping on its own. On occasion, it does raise issues that I have to make a decision on. After doing systems evals on review, I've stopped looking at code during review for 4 months now.

I do spend a lot of time up front specifying what I want. My prompts aren't one-liners, but rather an interview process where we work through all the open questions and ambiguity.

I haven't hit the wall that the OP talked about (when agents just can't seem to make the right changes, and it's impossible for me to go in and change things manually). I used a lot of guardrails such as plan reviews, browser-based QA, adversarial reviews, unit tests, linters, typecheckers, post-commit hooks, and formal method traces. I also specified engineering principles that steers the code base to minimize state and side-effects: functional core; imperative shell, make impossible states impossible, use pure functional style, etc.

There are times, when I can feel a part of the code base is messy without looking at it, because the agent will make recurring mistakes in the same part of the code base over time. What I found the agent was doing over time is that it's been layering state variables as requirements were discovered. So what helps is to ask it to refactor all these state variables into a single sum type. And if the state machine for it is complicated, I'll ask it to write a formal model of the state in Quint. Then I'll generate traces that get run as unit tests, and ask it to write the code against that.

So while the code base isn't exactly Brownfield, it's over a year old now. As for the code base, there's a backend and a frontend. I think it helps that I established a clear pattern I wanted. You code are like memes: agents will just copy patterns they see in the code base. When it does have to create a new part of the system, I found Sonnet-level models tend to draw system boundaries in all the wrong places. Opus is better. I don't yet know about Fable.

Happy to answer any questions about my workflow.

For those interested in incremental systems, I recommend checking out DBSP. I thought it was pretty neat.