rowanG077

Calling it something extremely negative like a cattle pen makes clear that you aren't even open to consider anything but the negatives.

You can do that? You have a million people ready to go? Whereas a singular person on a rich country salary can actually go out and start vast amounts of agents. I'm honestly perplexed by your argument. Most people would struggle to find even 5 people who will join them on a journey to build something that takes a long time. And you are just casually throwing out there "Well someone can just gather a million people".

Well not really. The point is "There are some things that are sped up by a very large factor, easily over 1000000x.", this is obviously referring to wall clock time. Not "agent time".

Yes companies/large groups of humans are sometimes also a lot faster at doing some things than a singular person. I'm not sure why that matters or what your point with that is.

I don't think you are supposed to multiple the number of agents with the time. After all a single human can run arbitrary number of agents. Still 1000000x speedup is a few order of magnitude too many imo.

That's moving the goal post. I was responding to this line in your comment:

> so turning over control to AI companies where no human ever sees the patient is a no brainer

Using an open weight model turns no control over to an AI company, even if that model was created by some AI company.

I'm not sure what AI companies have to do with it. Open weight models are available and work great, literally today kimi K3.1 pro was announced and goes toe to toe with closed models. You are tying AI usage to bigAI and that is unfounded.

I think it won't happen because people just care to much for performance. You already see this now. You see a ton of rewrites moving to rust even from higher level languages.

People are really not as black and white as you are making them out to be. Most coders cared both about writing the code and the end result.

Of course, and then AI will give you generic canned things to build. It cannot (yet) read minds. I don't understand what you wanted to make clear to me with this.

We are not talking about MVP, we are talking about finished products. Each of those can be done by a single person now in weeks. Before it was years.

I think one form of cognitive labor will remain: What do we actually want to do/build. And this is simply because AI does not know our internal world. Maybe in a few years with some kind of BCI that is extremely good. But I don't see it happening at least for a few years.

Yes, because someone who is so dedicated they make a throwaway account to bash Musk is someone whose mind is open to be changed.

I don't get it. Musk has an insane track record of shipping things. Well later then he claimed but he usually gets it done. I'm not seeing anyone else leading companies that upended the domination of fossil fueled cars, paved the way for brain implants, build re-usable rockets and create global access to the internet.

I see this sentiment a lot more recently and I don't understand it. Why is it "backhanded" if someone uses AI to create something. I don't see the connection with ease of creation either.

I certainly would not appreciate hourly crashes, don't get me wrong. But inconstant frame pacing makes me queasy. It's not low frametimes that is the issue, it's the inconsistency.

It depends a lot on the person I guess. But I'd gladly trade, let's say hourly crashes, for great frametimes.

Video games are pure functions of list[inputs] -> list[output]. Where the input are timestamped HID events and the outputs are video and audio, and in some cases stuff like rumble. The equivalence suite can treat the entire game implementation like a black box. Let AI generate millions of sequences of inputs that play through the game in various ways. Check for equality on the outputs with the same game but on the prior bevy version. Simple, very effective. Slight quirks game be dealt with as needed by allowing slight timing mismatches, slight or specifically allowed pixel differences allowed under certain traces etc.

I'm really not sure what was not clear about my statement of "Make the AI play the game pre and post bevy update. And difference down to a pixel can be flagged."

I would love to see them come up with this. And I will gladly await AI to smash through it in short order.

That's not a definition, that's a gut feeling.

I have heard that before, it's essentially the LLM cannot be creative packaged differently. But it always falls flat because there is just no way to measure it let alone define it. In the end it always give me a vibe of them wanting that to be the case rather than it being it case.

You have the model play both versions of the game in the same way at the same time. The equality would of course not come from the model, it comes from your testing harness. You just use the model to automatically play the game. SO you are checking game version A(inputs) == game version B(inputs). Where the AI generates the inputs that play through the game 10 times in different ways for example.

We are talking about practicality here. Not impossibility. "Just some dedicated time for it" essentially means man years of focused effort.

You’ve taken my statement, that an LLM can help test a game by running hundreds of hours of gameplay equivalence between versions(which btw means the AI doesn't say "it makes sense", your equivalence checker does), and stretched it into a claim that I’m saying games can be made entirely by LLMs through vibe coding with zero human testing. That’s such a blatant misrepresentation of my argument that I struggle to take your comment in good faith.

Sure they can. Make the AI play the game pre and post bevy update. And difference down to a pixel can be flagged. In fact you can get hundreds of hours of testing this way using sub-agents.

Go is not higher level. If anything I would consider Rust higher on the abstraction ladder than Go. Or rather it's perhaps better to say that Rust is higher level but can go down to a lower level than Go.

Money and time are precisely the point. Things are not practically possible of a X would cost 100K to develop and it's worth was 30K. But now that it costs 2K to develop it is suddenly practically possible.

1. A person building alternatives to photoshop single handedly: https://gizmodo.com/someone-vibe-coded-a-free-knockoff-of-ad...

2. The abundance of game decomps and recomps becoming available. Literally dozens of example in this space.

3. Reverse engineering of obscure software. A ton of oppertunities lie here.

4. As this posts indicate, severely accelerating existing software by re-writing it in language that are not terrible for performance.

5. Analyzing large volumes of unstructured information.

6. Creating one-off engineering and scientific tools.

7. Beating essentially all traditional Linux distribution, see Omarchy.

8. A personal example: I'm remaking the engine of an old game commercial game in rust.

I'm honestly a bit taken aback that this question is even asked. The volume of software is exploding and the power of the individual has increased a hundredfold.

I don't see at all that this is stifling love of tech. Sure if you liked to engage in language wars or vim vs emacs or tabs vs spaces then yes that's over. But tech as we know it is currently exploding, a ton of stuff that simply was not practically possible before is now possible.

The comment I responded on put forth a generic argument that implied if we can not learn from it it has no value. That is what I was responding to.

The point is that it's clearly not just a less maintained, less tested implementation. It's 1.61x faster for one in real world apps, in some case even almost 4x faster.

Generally building something is not about "What does this teach us?" but rather "What can this be used for?". You don't build a house and as "What does this teach us?". It's honestly almost a perverse question to primarily ask for something that aims to have practical value.

The clear reason this has worth is that it's much faster than TSC.