Whoever was insta-killing me in the gemini version over and over.... FUUUU!!!!
they forgot to ask gemini to implement a rootkit for anti-cheat!
Codex, Opus, Gemini try to build Counter Strike
111–120 of 144 posts
Re: Codex, Opus, Gemini try to build Counter Strike
#112Damn this is cool. Imagine an LLM trained extremely well on something like Unreal Engine.
A lot of the work done when making games in Unreal is done in the editor, not in source code. Also, Unreal source code will be the very last thing LLMs understand. This is the most complex software ever. There’s an algorithm called Nanite for automatically reducing the triangle count on geometry that’s far from the camera. As in there are not manually made separate level-of-detail models. The algorithm can modify mod…
Here's a blog post[1] from last year regarding an open-source implementation of virtual geometry. The linked code is maybe a couple thousand lines. It's not something you'd write in an afternoon, but it's also not the towering monument of complexity that Epic Games pretends it is.
[1]: https://jms55.github.io/posts/2024-06-09-virtual-geometry-be...
Edit: I don't mean to sound disparaging - it's some genuinely cool algorithms. It's just that Epic is incentivized to hype it up, and so you get a huge paper and multiple talks that are designed to make it seem even more impressive.
Re: Codex, Opus, Gemini try to build Counter Strike
#113These guys don't know what they don't know: "Now let's make shots work. When I shoot, send the shot as a topic, and make it affect the target's HP. When the target HP goes to zero, they should die and respawn." This is not how shooting is implemented in a competitive first person shooter.
"At the end, all models built real a multiplayer FPS, with zero code written by hand! That’s pretty darn cool." If you don't understand how a multiplayer FPS works, how can you tell if the AI has actually created one for you or not?
Many children who play videogames can tell you what a multiplayer FPS is, and most of them don't know how to code it.
Re: Codex, Opus, Gemini try to build Counter Strike
#114This makes me depressed. LLMs will take the most enjoyable part of my job and I will be stuck reviewing or fixing bugs in their "it-compiles" codebase.
On the contrary, coding for me has become more fun than ever since Opus 4.5. I'm working more and genuinely enjoying it a lot more, haven't had this much fum building software in years. (I work at Anthropic but have also tried Gemini, it's also fun)
Same. I've resurrected side projects and done months of work on them overnight, getting to my true end goals. Creating software is fun. Wrangling a bunch of opinionated libraries and plumbing together systems with terrible ergonomics (i.e. webpack, maybe web development generally?) is bs work I'm glad to not have to do.
Re: Codex, Opus, Gemini try to build Counter Strike
#115Earlier quoted context omitted.
Anthropic shared some approximate numbers on their Smart Contracts post. A 5h research assignment currently has an API cost of ~3.500USD.
What does 3.500USD mean? Are we bringing back the half-penny?
You’re also not correct even if it were a decimal marker. Three dollars and fifty cents requires no half cent.
Re: Codex, Opus, Gemini try to build Counter Strike
#116This is the kind of thing that's so impressive that if you're not an (experienced) SWE you think "man LLMs are the future, and I am making some major decisions based on this". But you look at the code, and it's essentially gluing three.js and some DB stuff together. There's no lobby, no real interaction logic, no physics apart from what you get from three.js, chatting, commands, map editing, game modes. In other word…
> man LLMs are the future They are. I know a lot of people don't want to admit this, but they are. They're getting better with each release. > But we're learning it's not economical--this is some of the costliest slop we've ever made. Huh? How on earth would you know whether my usage of LLM's has been worth it or not? > Sometimes slop can be useful; maybe you can shape it into something useful Man, I just spent the l…
> You're guaranteeing I have a job because you refuse to acknowledge the very obvious thing that's happening.
I’ll take that bet.
Re: Codex, Opus, Gemini try to build Counter Strike
#117Earlier quoted context omitted.
"At the end, all models built real a multiplayer FPS, with zero code written by hand! That’s pretty darn cool." If you don't understand how a multiplayer FPS works, how can you tell if the AI has actually created one for you or not?
Many children who play videogames can tell you what a multiplayer FPS is, and most of them don't know how to code it.
I did not say what a multiplayer FPS is. I said "how a multiplayer FPS works".
There is a difference.
Re: Codex, Opus, Gemini try to build Counter Strike
#118Earlier quoted context omitted.
Many children who play videogames can tell you what a multiplayer FPS is, and most of them don't know how to code it.
I did not say what a multiplayer FPS is. I said "how a multiplayer FPS works". There is a difference.
I agree that this is not how shooting is implemented in a production competitive shooter, but that wasn't the goal of the post. We wanted to test how far models could go, and I think this current version is the limit in a 2 hour time window.
Re: Codex, Opus, Gemini try to build Counter Strike
#119Earlier quoted context omitted.
This is overparameterisation
No
I guess you have not tried GPT 5 Pro
GPT’s differentiator is they focused on training for “thinking” while Gemini prioritized instant response. Medium thinking is not the limit of utility
Re: overparameterization specifically Medium and High are also identically parameterized
Medium will also dynamically use even higher thinking than High. High is fixed at a higher level rather than leaving it to be dynamic, though somewhat less than Medium’s upper limit
Re: Codex, Opus, Gemini try to build Counter Strike
#120This makes me depressed. LLMs will take the most enjoyable part of my job and I will be stuck reviewing or fixing bugs in their "it-compiles" codebase.
I am sorry this made you feel depressed. I think there are some positives to consider too though:
1. More people that wanted to make games can.
Thanks to unreal engine, you don't need to be a Tim Sweeney level-expert to make compelling games. I see LLMs as another abstraction in the same spirit.
2. You get more leverage
The more abstractions you have, the more you can do with less. This means less bureaucracy, more of a chance to make _exactly_ what you wanted.
I understand how the craft changes underneath you, and that can feel depressing, but if we see it as tools, I think there's lots of good ahead.