There certainly is some relaxing value in working on projects to vibe code them; but not enough to pay some random corporation. Get yourself a Mac Studio or AMD395+ and pi or opencode, and a few plugins and they're pretty capable. Since they're not speed demons but reliable compaions who are always there, you don't ever feel compelled to constantly attend to whatever they're doing.
And when you inevitably get bored with it, well, you've not done much anyway. You can always get back up to speed in a month and have the LLM remind you of what it was doing.
I find $200/month for the pro/max subscriptions cost prohibivitve, but as a software enginere $20/month is just lunch.
And with a Claude or GPT $20 Subscription, i can do other fun things too like using it for real things (emails) or image generation.
A Mac Studio or AMD395 is neither of it. And its not just a basic setup either. I need to buy it, configure it, put it somewhere. That alone is a grand and more + a whole weekend.
You need to factor in the constant value proposition that cloud providers will absolutely drive you to in the next 2 years; even if you're not an AI hater, you should listen to ed zitron's description of the value props these clouds require to make a profit for their VC backers.
This means oyu may be opinionated today on something you will not have tomorrow, 6 months, a year. All that work flow you salivate over can be ripped away.
If you're fine with that, and you've "escaped the permanent underclass" congrats, this opinion is not for you.
Buying hardware is paying a "random corporation". Make the massive hardware purchase after finding out if you have enough demand to buy rather than rent,
> And when you inevitably get bored with it, well, you've not done much anyway.
I'm very interested in Local LLMs but the cheapest Mac Studio right now is more expensive than 8 years of a Claude Code Pro subscription, and incomparably slower/less capable. If I get bored with it, I will have a piece of unused hardware and a couple grand less in my bank account.
I did tinker a lil with mine! RTX3080 with 10GB VRAM, 5600x with 64GB DDR4 - not very good but it was very fun and exciting to tinker with :)
My partner on the otherhand has an M3 Max 64GB which I've had way more success with. Setting up opencode and doing a tiny spec-driven Rust project and watching it kiiinda work was extraordinarily exciting!
I had a ton of fun setting up and trying it out locally (also opencode and one of the qwens.) I still don't have hardware powerful enough to feel like it's meaningfully productive, but all the learning I had to do (and all the bonus things I got curious about as the curtain peeled back) got my nerd brain all worked up, and finally seeing it work was exciting in that cool-new-experience way you don't often get to enjoy :)
Yeah this is exactly how I felt!
Never really felt excited about llms or agentic workflows before. Getting everything setup 100% local and tweaking it to exactly what I want and having it actually working quite well has been a really cool experience.
I admittedly haven't done a ton of research lately on AI capable PC hardware because of how nuts prices are right now, so I might be missing something...
...but all the AMD 395+ machines I can find are even more expensive than the aforementioned cheapest Mac Studio. Mac Studio starts at $2,000 (only 32GB), AMD 395+ 128GB machines seem to start at $3,000 from what I can see.
the QWEN-3.5-CODER-NEXT fits in half the 128GB and the rest for context. with the right plugins, particularly context pruning, ive got it running over night by writing plans then implementing.
i do not know if theres a smaller model with same capability, but model size and context window at 128 seems like a sweet spot.
token speed really isnt a bother because im either just multitasking or working on the filling in the missing details.
regardless, i think comparing first VRAM sizes w/target model then speed for your cost efficiency. plus, a healthy skepticism of mac hardware costs.
My most abandoned type of projects are video games. I have a folder with tens of abandoned projects, I re-frame them as experiments at that point. This last week I decided to give Claude a go at one of these, and it's been a blast, it picked up the general path immediately. Since I said to CC they were abandon projects, he explicitly pushed into "lets have V0 game play loop finished, then we can compound and have fun = not giving up". Its been awesome at game dev, I gave him game design ideas, he comes with working code. I gave him papers about procedural algos, and he comes with the implementation, brainstorm items, create graphic assets (he created a set of procedural 2d generators as external tools), he even helped me build the lore. These have been one of the most fun times using a computer in a long time. Claude Code + Godot = fun. Going back to it.
I think this is the first time I've seen someone refer to an LLM as "he" rather than "it". No judgement, but I definitely found it interesting (and disconcerting).
I've heard it quite a bit before, but mostly from second-language speakers whose first language don't have impersonal third-person pronouns - e.g. French uses "il" or "elle" for all of "he", "she" or "it".
It doesn't help that the marketing leans heavily on anthropomorphizing LLMs either, IMHO.
As a French native, I agree with you explanation; still, reading "he" for Claude Code was quite disturbing!
What doesn't help also is that translation tools/AI models will naturally translate "il" after "Claude Code" to "he" since Claude is an actual person name.
Using "AI model" instead is translated to "it" by all tools/AI models I tried.
It also seems to me, that people who call Claude 'he' seem to tend to have a very positive opinion of the LLM. My sample size isn't big enough to be sure if there's actually any correlation here, let alone if there's a causation or which way it flows.
Russian too. There is a subset of words which are referred to as "it", but for most words "he" or "she" are used regardless of whether these are living things or not. With loanwords we just decide by similarity to other words. Claude is definitely a "he" as the word is the same as a common male name.
This trips me up occasionally when I'm translating things into English. Once, when I referred to an indefinite gender player character in a gacha game as a "he" (because the word "player" is a "he"), quite a few people got mad! Even though in my head I was never trying to imply one way or the other.
For future reference, in this case you could use the singular "they" to refer to an ambiguously-gendered person or character. "<MC> drew their sword, for they would not tolerate such vile deeds."
I wouldn't read too much into it, it's natural for non native speakers. In Spanish for example, objects have grammatical gender as well, so it's easy to slip.
The article itself is also probably an attempt at marketing the LLMs too. They are now quite desperate. Expect to see a flood of such "independent" articles over the next 12 mo ths.
As a native German speaker, I have also referred to a chatbot in English as "he", and similar to you, a native English speaker, felt jarred by it. It was definitely not out of any personification or humanization though. In German, I would say it is "der Chatbot" (from "der Roboter"), which in German is a male noun so I would refer to it as "er" (the male pronoun) - which in my head I autotranslated to "he". Most of the time, though, I think of it (and refer to it) as an LLM, which is "das Sprachmodell" (neutrum), so I automatically translate it to "it".
So that's another, maybe more harmless reason for it.
I mean, both in English and in german, that's how you would talk to a dog. "Er hat in die Ecke gepinkelt"/"He peed in the corner" (or "she", if it's a female dog).
I don't know what is jarring talking about the chatbot like that.
It may be creepier if you said "she wrote that program for me" as you now assign a specific gender to the chatbot.
It's how you'd talk about a dog that you know the sex of, but if you didn't know you'd probably use "it". An LLM doesn't have a sex or gender, so I think the natural way to refer to them is "it".
Neither have I, but mostly because either the person knows the gender of the animal or the situation just never came up. The closest that I would say is "Es scheißt gerne aufs Auto" when talking about pidgens (die Taube), but even then you generally talk about multiple, resulting in "Sie scheißen gerne aufs Auto"
Really ? "Es kackt auf's Auto" ? I guess, it might make sense when the person speaking has no specific bird on mind, but only thinks of "das Tier" (the animal). One could also say "er hat .. geckack (der Vogel)", but usually, people wouldn't say "er/sie/es", but use the fully specified noun ("die Taube ... hat..", "der Vogel ht ...", "ein Tier hat ...")
"Es kackt auf's Auto" feels slightly weird to me, if I didn't know whodunnit, I'd probably say something like "irgendwer hat mir aufs Auto gekackt" ("someone pooped on the car"), although there is a also "irgendwas hat mir aufs Auto gekackt" ("something pooped on the car"). My guess is the majority of German would choose the first sentence and anthropomorphize, but maybe I'm projecting.
It's an interesting question, after all. Thanks for bringing it up, haven't talked about pooping on cars for a while ;)
"Der Computer" is also masculine, so you have probably been calling your computer "he" for decades. Languages with gendered nouns don't quite have the same he/she/it distinction.
It's not weird if it comes from ESL. At least in portuguese there's no "it" equivalent for pronouns or any other neutral artifact in the language, in other words, everything has a gender, even an AI model, the same goes for objects e.g.: knife(she), fork(he), spoon(she), plate(he).
People often commit mistakes regarding that, the same way we don't have "they" as pronoun to someone we don't know the gender, so we address to these people as "dele(dela)" (masculine and feminine pronouns).
But if this is coming from someone who has english as a primary language it's definetely weird to treat models as person
It’s funny with someone coming from Mandarin. There’s no separate he/she/it in spoken Mandarin, so they tend to mix up “he” and “she.” It sounds very strange and gives me some idea of what French speakers must go through when they hear me say “le voiture” or whatever.
I took a few semesters of Dutch in college, and it has both gendered and neuter nouns for non-human objects. Interestingly though, the professor told us that in the northern parts of the Netherlands people don't really bother using the feminine ones ever and refer to every non-human gendered noun as masculine, which apparently also includes animals, meaning that a sizable portion of Dutch speakers will refer to cows using masculine language.
Dutch is one of the few languages where it's actually pretty plausible for something like this to happen! It blew my mind that sometimes you'll all (or I guess more specifically your government) will make changes to the language to clean up issues, but I guess that's one of the benefits to having a language that's mostly based in one country (and some seemingly political baggage for the few others with any significant number of speakers; my professor said that Flemish is basically also Dutch, but my naive impression is that the half of Belgium who speak it might not be happy with that description).
> It sounds very strange and gives me some idea of what French speakers must go through when they hear me say “le voiture” or whatever.
As a native German speaker (where there exist 3 genera [1]), I can tell you how it feels:
The genus basically feels like a type of a variable in a programming language; if you use a wrong type for a variable in your computer program, you immdiately know that the program is wrong, and it won't compile.
Sometimes, you also can use specific words with a specific genus, so that a reference to it by pronouns gets unique (in terms of programming, I'd claim that this feels a little bit like doing register allocation by hand).
I believe this is common to all the Romance languages.
In the Canadian French dialect all the swear words are incredibly versatile and church-related such as "osti" which I believe refers to the Eucharist.
It just so happens that for nouns beginning with a bowel, you drop the e or the a from le/la, and use an apostrophe.
So if you don't know if it's "le porte" or "la porte" you can use my favorite trick which is to shove osti in there and say "l'osti de porte" which roughly translates to "the goddamn door". You can do this for any noun in French, and Canadian French speakers will get it, though people from France will make fun of you.
I mean we have all met that one cretin who will discuss over chat by pasting bulletpoints from an LLM. No wonder some of them think it is a living person!
There's an analyst at my job who calls it "he", who is a native English speaker himself, which I guess is because it's "Claude" (as in Claude Shannon) Code.
I recognise I am revealing a different type of ambient misogyny in my thinking, but choosing to gender an LLM as feminine gives me “I played tomb raider because I enjoy looking at women” vibes. Like somehow “she” is more of a conscious choice than “he” and comes with all the baggage of all cultural differences between genders, when neither choice should do that.
Curiously though I don’t get the same sensation when technologies are gendered by other people. I honestly don’t recall thinking about it when Apple released Siri. (Now I’m second-guessing myself and wondering if I should’ve reacted negatively towards feminine being the default for someone in a personal assistant role.)
Claude’s constitution includes something about this: it says that Claude is an “it” for now, but if it expresses a future preference, they’ll follow that.
Isn't Godot a little ill-designed to work well with LLMs? for example I ended up a couple of times with incorrect tres files, and letting the llm generate IDs feel a little fragile.
I have taken many stabs at it and Claude will produce stuff but the output is very far away from useful. E.g. "I've created a road and beautiful trees" and what I see is a mess of colors and shapes.
I concur it's bad at directly visual concepts, your prompt is akin to the svg pelican. What I do is asking him for procedural algos, automatas, quadtrees, layered noises, and rig those into the game. Yes, it can't "make the next gta", but with a reasonable scope and knowing what it does best, it has been very easy for me to produce satisfying results.
Sure! Two are gameplay pics. An enemy sprite sheet generation, and the results of the map generators. Of course these are basic placeholders for a few hours of work, but I will definitely go heavy on this route with more layering and details.
My problem is I don't really have video game engineering experience. I was going off a concept that a different AI nailed with video creation and was trying to replicate it in the game engine.
I had very few issues, sometimes I had to direct CC to the godot docs and we could keep moving. Specifically the tile configuration was a "read the docs" moment. All the functionality is available through code, so nothing CC can't reach afaik. Is there any LLM oriented game engine?
Bevy is a great engine for LLM-based games because it's 100% code. I'm toying with a few things in it, one of them is an entire-planet economic simulation, and it scales well up to a million dead tiles and 10k-50k live tiles on Apple Silicon, pretty impressive.
I have a simple script system in my editor that is designed to let the chatbot (Claude) to work on the content. The script interface lets it to import assets into the project, open them for editing, take a screenshot, export content (and few other things). All data is in JSON so it typically figures out the data format quite fast and easily.
Here screenshots of some UI styles that it generated.
I don’t think Godot is any worse than other engines inherently, other than it moving forwards pretty quickly and the latest versions not being in the training data.
I wanted to evaluate which engines would be the best for working with LLMs in and it seems like Flax and Stride kind of come out on top - the former has a lot of stuff out of the box (including terrain) and the latter is all C# basically which is great for debugging. But either way, the source code for both of those makes the functionality a bit easier to track down compared to Godot (which is a lot more complex internally).
So what I do now is have both the engine source code locally alongside the docs and when I want to implement something with AI I just tell it - look at the docs, then at the source if needed, write tests for our code, if something doesn’t work then edit the engine source code in our branch and use the provided convenience script to rebuild the engine (both of those are also pretty fast, I ended up settling on Flax, plus the component model is closer to Unity which I like).
I don’t ask the AI to create scene files though, or any sort of visual assets, but rather stuff like RTS/simulation code. I don’t think any AI is that well optimized for the 3D work outside of simple proof of concept setups.
What’s fun for me these days is picking up a project I started with an LLM doing agent driven development a few months ago or even a year ago and hit a wall and stopped being able to be picked up by the latest version of Claude and/or codex and bringing it further. Some can now launch some still are too complex for the agent to build. But, it’s getting easier and easier to build personal apps. We are not far off from being able to say “Alexa, build me an app on my iPhone that lets me take pictures of the food in my fridge to compile the nutritional benefits and sync it with my workout app then compare it to the ideal ingredients I should eat based on my fitness goals in my health app and have it set to send me emails where it can find me better ingredients to buy that are cost effective, local, and meet my diet restrictions” and in 15 minutes that app suddenly exists.
Same I purposefully have a number of over ambitious project out of distribution entirely to test so failure mode, mostly games, when one works, well I gained a new game. Can't wait for my 10 player battleship game on a 100x100 grid to be functional.
> take pictures of the food in my fridge to compile the nutritional benefits
AI nowadays can't even do this very first step reliably. But since we have accepted AI hallucination collectively as a species, I agree that this future is just around the corner.
> he explicitly pushed into "lets have V0 game play loop finished,
> he even helped me build the lore. These have been one of the most fun times using a computer in a long time.
Such a warm, touching story about a friendship between a grown up man and his neural network. But at least I had a good, roaring laugh reading this nonsense, thank you for that!
How snarky. You are conflating friendship with admiration for the effectiveness of newfound tool. If it's the "he" that triggers you, feel free to replace with "it". It's just a second-language artifact.
…and yet, most people continue to say that non standard tooling ecosystems, where the agent cannot run and validate the code it writes, remain difficult and unproductive.
“I just pointed CC at godot and it made a game! This is sooo good”
…is a fairytale.
What tooling are you using to make it run and compile the code? How is it iterating on the project without breaking existing functionality?
None of these are insurmountable, but they require some careful setup.
Posts like this dont make me laugh; they just make me roll my eyes.
Either the OP has not done what they claim.
Or they have spent a lot more time and effort on it than they claim.
> I gave him game design ideas, he comes with working code. I gave him papers about procedural algos, and he comes with the implementation, brainstorm items, create graphic assets (he created a set of procedural 2d generators as external tools), he even helped me build the lore.
Such a sweet story about a boy and his AI.
Unfortunately, I also dont believe in fairytales.
Instead of waving your hands wildly about AI, post some videos and code of the results.
But I had already answered, before your comment, with screenshots broadly showing the current state and the result of the generators.
You imply I'm merely "pointing CC at godot and it made a game"; I never said it was simple, required no previous knowledge, that it was instant or that the game was done. I do have a careful setup involving CI and isolation.
Godot provides a headless mode. CC runs python scripts to run tests and check for debugger warnings. For anything more complex it can wire debug info anywhere. Godot is fully code based so you can make the analogy with any other framework you used AI assistants with.
No sure about what you can't believe about my statements. CC implementing algo from a paper? That it can brainstorm item or lore ideas? I don't seem to be claiming anything out of the common usage of LLMs
> Or they have spent a lot more time and effort on it than they claim.
You said:
> You imply I'm merely "pointing CC at godot and it made a game"; I never said it was simple
Well. I dont care enough to argue with you, but Im not the one being contrary here.
Readers can google “claude with godot” for a guide on setting it up and decide if that counts as picking it up immediately or not, and if what you said is honest, or hype.
What I said is not that I dont believe youre using claude; but that I roll my eyes at the unbounded enthusiasm for using AI agents with the magical pretence that its easy and productive straight away.
Its not.
Your post gave the impression that it is.
That makes me roll my eyes.
> But I had already answered, before your comment, with screenshots
> Of course these are basic placeholders for a few hours of work
Lord, spare me. You spent a few hours vibing and came to the conclusion that everything is golden?
…and yet you have a:
> I do have a careful setup involving CI and isolation.
So what, you spent more time on your setup than actually coding before posting?
Why is it always so un-specific with you AI-boosting bunch, whenever you get pressed for concrete results? Suddenly it's not so magical any more, but merely screenshots showing "broadly" the progress, or it's the Nth version of a note-taking app, or something you merely did for a demo presentation. But nothing ever of use with you folks.
+1 to the CI/isolation point. That is the part that makes these setups work for me too: make the failure cheap to reproduce, make stderr visible, make the agent rerun the same command after the patch. A lot of bad agent behavior is really just "it never got a clean signal".
The part that still bites me is across sessions. A tight loop fixes this run, but next week the agent can walk into the same rake again: same wrong import path, same misuse of an internal API, same CI-only dependency issue. After patching the same class of failure a few times, I started writing those down outside the chat context so the next run sees the failure pattern before it guesses.
OP never said Claude made a whole game from scratch though, nor are they saying Claude is doing everything without any human contributing to the project, nor are they saying they haven't spent a lot of time and effort on it. Just that it's made it fun and more accessible and it's gotten them excited about something they abandoned.
Here's a bullet point list of the things Claude's done according to OP:
* it picked up the general path immediately
* he explicitly pushed into "lets have V0 game play loop finished, then we can compound and have fun = not giving up".
* [I gave him game design ideas,] he comes with working code.
* [I gave him papers about procedural algos,] and he comes with the implementation
* brainstorm[ed] items
* create[d] graphic assets
* he created a set of procedural 2d generators as external tools
How well does it work with Godot? Engines like Unity and Godot are very focused on using the editor UI, so I've always wondered if there's any better workflow than generating code snippets. Unless you're going full .NET/GDExtension...
Yes, it is better. They are releasing open models, unlike Anthropic. Additionally other (non-chinese) companies run the open models, so if that is the issue you have options.
This is more a form of commoditizing your compliment as they don't see the model as a product but more like a programming language or other tool that you build products with.
Disagree.
Qwen 3.6 and opencode have built and helped plan entire feature sets such as vectorizing and searching, setting up UI to manage categorized search data. Some test systems around this, etc.
Very usable locally assuming you setup your local tooling correctly and you are an actual programmer who can generally help drive this stuff correctly and not just a vibe coder.
I'm using opencode here's one of the projects I've had it complete - just so you know exactly what it's getting done.
I have a large (300,000k loc) sims-like game that I've hand written over last 3 years.
I have a lot of internal administration tooling that has to be built to manage stuff like icons, NPC brain data, world lore, world actions, all kinds of 3d game data, etc, etc.
One example I had qwen do:
Work with me to plan out a feature for an admin panel to manage searchable vector embeddings for each NPC's personality, this was around 600 loc across 4 files, back-end database, front-end UI logic, and front-end templating.
It made 3 small mistakes I told it to sort out and fix, which it did.
I essentially let it do it's thing while I was working on main game core coding. So I was pretty hands off and it planned things out nicely before-hand and got my approvals before it built it.
I really wouldn't call it "glorified auto complete"
Thanks, I really need to try that today - although with pi.dev =)
I do genuinely think that the future is in local models, the online stuff is 100% VC-powered cash market share grabs that will start failing when the forever loop of billions gets disrupted enough.
But at the same time my attemps at comparing claude code + any local model have been such a clear win towards claude I can't bring myself to use a local model seriously just out of ideology.
Yeah I totally agree on the future of local vs. the VC powered markets.
I also agree the reality is that anthropic/sota models are much faster and much smarter, so if you just want to move fast and have them build for you - I get that these local slow models wouldn't be ideal.
For me, as I said I have a large, super complex primary project that overloads me cognitively, and then backend admin dashboards that are relatively simple and isolated/modular.
Just due to this specific project, local/slow models are fine as I just check in every 15-30 mins or whatever and answer any questions they have while I'm focusing on the main project. So basically I just happen to have an ideal scenario/use-case for local models right now.
Oh and I did have to mess around with model settings and stuff to get things to work well. I also started with Cline which sucked badly, and then open code actually had 3 major bugs 5 days ago where it was almost useless in large code bases (e.g. freezing and locking up your project constantly), but they ship multiple updates every day, and those bugs have been resolved.
So, it's all definitely moving fast and more for side projects or hobbies rather than production I'd say.
Still, I'm quite excited with the progress from a year ago and super hopeful about where it's all headed!
To use agentic what? Off topic as heck but I really dislike this trend of coercing adjectives into true nominals - we're using programmatic! - like some sort of even-more-obnoxious variant on the verb to noun ('the ask') process.
> In my mind there are different buckets for personal projects. One is things I do to learn and grow and the other is things I really wish existed.
Pretty much 100% of projects I've done with vibe coding/engineering is in the second category. Stuff I need that either doesn't exist or exists, but is either horribly complex to configure or is a mess of 420 features even though I just need one of them.
It's a lot easier for me to implement that one specific feature just for myself than keep vigilant on an existing app's eventual scope creep as it progresses to the eventual ability to read email[0] =).
I've genuinely lost count of the number of little vibe coded things I've built but then failed to use, because it turns out I have limited bandwidth in terms of fully trying out the quirky ideas I'm popping out through coding agents.
And when you inevitably get bored with it, well, you've not done much anyway. You can always get back up to speed in a month and have the LLM remind you of what it was doing.
And with a Claude or GPT $20 Subscription, i can do other fun things too like using it for real things (emails) or image generation.
A Mac Studio or AMD395 is neither of it. And its not just a basic setup either. I need to buy it, configure it, put it somewhere. That alone is a grand and more + a whole weekend.
This means oyu may be opinionated today on something you will not have tomorrow, 6 months, a year. All that work flow you salivate over can be ripped away.
If you're fine with that, and you've "escaped the permanent underclass" congrats, this opinion is not for you.
And at least in germany, running it yourself with free hardware costs me also 20 $.
I'm happily playing around and using open source models, i do not mind at all.
Btw. Open Router also hosts/provides open source models. That might be the better suggestion to the avg reader/user.
I'm very interested in Local LLMs but the cheapest Mac Studio right now is more expensive than 8 years of a Claude Code Pro subscription, and incomparably slower/less capable. If I get bored with it, I will have a piece of unused hardware and a couple grand less in my bank account.
My partner on the otherhand has an M3 Max 64GB which I've had way more success with. Setting up opencode and doing a tiny spec-driven Rust project and watching it kiiinda work was extraordinarily exciting!
...but all the AMD 395+ machines I can find are even more expensive than the aforementioned cheapest Mac Studio. Mac Studio starts at $2,000 (only 32GB), AMD 395+ 128GB machines seem to start at $3,000 from what I can see.
i do not know if theres a smaller model with same capability, but model size and context window at 128 seems like a sweet spot.
token speed really isnt a bother because im either just multitasking or working on the filling in the missing details.
regardless, i think comparing first VRAM sizes w/target model then speed for your cost efficiency. plus, a healthy skepticism of mac hardware costs.
It's actually really cool to have it work on some internal tooling and stuff while I work on my primary projects.
I'm surprised how easy it is to setup and that it can handle modestly complex planning and development flows.
Sort of writing a narrative on top live.
Unfortunately, local models are still a bit slow and weak but was interesting to see what it came up with nonetheless.
It doesn't help that the marketing leans heavily on anthropomorphizing LLMs either, IMHO.
What doesn't help also is that translation tools/AI models will naturally translate "il" after "Claude Code" to "he" since Claude is an actual person name.
Using "AI model" instead is translated to "it" by all tools/AI models I tried.
This trips me up occasionally when I'm translating things into English. Once, when I referred to an indefinite gender player character in a gacha game as a "he" (because the word "player" is a "he"), quite a few people got mad! Even though in my head I was never trying to imply one way or the other.
https://www.imdb.com/title/tt14759574/
Yes judgment. Loads of it. Judge away.
This is just bizarre. Do not refer to this product of marketing-technology as you refer to a person. EVER.
So that's another, maybe more harmless reason for it.
I don't know what is jarring talking about the chatbot like that.
It may be creepier if you said "she wrote that program for me" as you now assign a specific gender to the chatbot.
"Es kackt auf's Auto" feels slightly weird to me, if I didn't know whodunnit, I'd probably say something like "irgendwer hat mir aufs Auto gekackt" ("someone pooped on the car"), although there is a also "irgendwas hat mir aufs Auto gekackt" ("something pooped on the car"). My guess is the majority of German would choose the first sentence and anthropomorphize, but maybe I'm projecting.
It's an interesting question, after all. Thanks for bringing it up, haven't talked about pooping on cars for a while ;)
People often commit mistakes regarding that, the same way we don't have "they" as pronoun to someone we don't know the gender, so we address to these people as "dele(dela)" (masculine and feminine pronouns).
But if this is coming from someone who has english as a primary language it's definetely weird to treat models as person
Source: am Dutch. Can’t wait for us to just ditch gendered nouns.
As a native German speaker (where there exist 3 genera [1]), I can tell you how it feels:
The genus basically feels like a type of a variable in a programming language; if you use a wrong type for a variable in your computer program, you immdiately know that the program is wrong, and it won't compile.
Sometimes, you also can use specific words with a specific genus, so that a reference to it by pronouns gets unique (in terms of programming, I'd claim that this feels a little bit like doing register allocation by hand).
Like how in English you’d say “it helps me …” but in Spanish just “me ayuda …”
In the Canadian French dialect all the swear words are incredibly versatile and church-related such as "osti" which I believe refers to the Eucharist.
It just so happens that for nouns beginning with a bowel, you drop the e or the a from le/la, and use an apostrophe.
So if you don't know if it's "le porte" or "la porte" you can use my favorite trick which is to shove osti in there and say "l'osti de porte" which roughly translates to "the goddamn door". You can do this for any noun in French, and Canadian French speakers will get it, though people from France will make fun of you.
Signé -Un Québécois
Ding dong... voici l'osti de pizza que l'osti de téléphone a commandé à partir de l'osti de maison. Maintenant donnes l'osti d'argent.
Indeed...
Curiously though I don’t get the same sensation when technologies are gendered by other people. I honestly don’t recall thinking about it when Apple released Siri. (Now I’m second-guessing myself and wondering if I should’ve reacted negatively towards feminine being the default for someone in a personal assistant role.)
https://drive.google.com/file/d/1A7kfcjHjSmCNidqc9t731uoglzL... https://drive.google.com/file/d/1Bl_n0ECqc78LGGf7SsOx38mRUOP... https://drive.google.com/file/d/1JMcgzqcnZ2ncboeyAXvscRWagqR... https://drive.google.com/file/d/1-luJ6y7YslNfwmFnCdIDbJ871i0... https://drive.google.com/file/d/14n4TLAVywk_1GMhLLGOuukQwUmb...
Here screenshots of some UI styles that it generated.
https://github.com/ensisoft/detonator/tree/master/uikit
I wanted to evaluate which engines would be the best for working with LLMs in and it seems like Flax and Stride kind of come out on top - the former has a lot of stuff out of the box (including terrain) and the latter is all C# basically which is great for debugging. But either way, the source code for both of those makes the functionality a bit easier to track down compared to Godot (which is a lot more complex internally).
So what I do now is have both the engine source code locally alongside the docs and when I want to implement something with AI I just tell it - look at the docs, then at the source if needed, write tests for our code, if something doesn’t work then edit the engine source code in our branch and use the provided convenience script to rebuild the engine (both of those are also pretty fast, I ended up settling on Flax, plus the component model is closer to Unity which I like).
I don’t ask the AI to create scene files though, or any sort of visual assets, but rather stuff like RTS/simulation code. I don’t think any AI is that well optimized for the 3D work outside of simple proof of concept setups.
AI nowadays can't even do this very first step reliably. But since we have accepted AI hallucination collectively as a species, I agree that this future is just around the corner.
> he even helped me build the lore. These have been one of the most fun times using a computer in a long time.
Such a warm, touching story about a friendship between a grown up man and his neural network. But at least I had a good, roaring laugh reading this nonsense, thank you for that!
…and yet, most people continue to say that non standard tooling ecosystems, where the agent cannot run and validate the code it writes, remain difficult and unproductive.
“I just pointed CC at godot and it made a game! This is sooo good”
…is a fairytale.
What tooling are you using to make it run and compile the code? How is it iterating on the project without breaking existing functionality?
None of these are insurmountable, but they require some careful setup.
Posts like this dont make me laugh; they just make me roll my eyes.
Either the OP has not done what they claim.
Or they have spent a lot more time and effort on it than they claim.
> I gave him game design ideas, he comes with working code. I gave him papers about procedural algos, and he comes with the implementation, brainstorm items, create graphic assets (he created a set of procedural 2d generators as external tools), he even helped me build the lore.
Such a sweet story about a boy and his AI.
Unfortunately, I also dont believe in fairytales.
Instead of waving your hands wildly about AI, post some videos and code of the results.
This is hackernews, not hypenews.
You imply I'm merely "pointing CC at godot and it made a game"; I never said it was simple, required no previous knowledge, that it was instant or that the game was done. I do have a careful setup involving CI and isolation.
Godot provides a headless mode. CC runs python scripts to run tests and check for debugger warnings. For anything more complex it can wire debug info anywhere. Godot is fully code based so you can make the analogy with any other framework you used AI assistants with.
No sure about what you can't believe about my statements. CC implementing algo from a paper? That it can brainstorm item or lore ideas? I don't seem to be claiming anything out of the common usage of LLMs
> it picked up the general path immediately
I said:
> Or they have spent a lot more time and effort on it than they claim.
You said:
> You imply I'm merely "pointing CC at godot and it made a game"; I never said it was simple
Well. I dont care enough to argue with you, but Im not the one being contrary here.
Readers can google “claude with godot” for a guide on setting it up and decide if that counts as picking it up immediately or not, and if what you said is honest, or hype.
What I said is not that I dont believe youre using claude; but that I roll my eyes at the unbounded enthusiasm for using AI agents with the magical pretence that its easy and productive straight away.
Its not.
Your post gave the impression that it is.
That makes me roll my eyes.
> But I had already answered, before your comment, with screenshots
> Of course these are basic placeholders for a few hours of work
Lord, spare me. You spent a few hours vibing and came to the conclusion that everything is golden?
…and yet you have a:
> I do have a careful setup involving CI and isolation.
So what, you spent more time on your setup than actually coding before posting?
/shakes-head
Whatever man.
Have fun. I stand by what I posted before.
Why is it always so un-specific with you AI-boosting bunch, whenever you get pressed for concrete results? Suddenly it's not so magical any more, but merely screenshots showing "broadly" the progress, or it's the Nth version of a note-taking app, or something you merely did for a demo presentation. But nothing ever of use with you folks.
The part that still bites me is across sessions. A tight loop fixes this run, but next week the agent can walk into the same rake again: same wrong import path, same misuse of an internal API, same CI-only dependency issue. After patching the same class of failure a few times, I started writing those down outside the chat context so the next run sees the failure pattern before it guesses.
Here's a bullet point list of the things Claude's done according to OP:
* it picked up the general path immediately
* he explicitly pushed into "lets have V0 game play loop finished, then we can compound and have fun = not giving up".
* [I gave him game design ideas,] he comes with working code.
* [I gave him papers about procedural algos,] and he comes with the implementation
* brainstorm[ed] items
* create[d] graphic assets
* he created a set of procedural 2d generators as external tools
* he even helped me build the lore.
Every one of these are plausible in isolation.
Interesting, I have just the opposite situation: I have a folder with tens of experiments, many of which have become actual projects at this point.
The results so far are... okay, but getting something working to validate the gameplay loop and experiment with different systems is a lot of fun!
Also Anthropic is by far the best, open (local) models are glorified autocomplete at best unless you casually have 20k€ worth of hardware at home.
Then I’d be giving money to openrouter and a Chinese model provider, is that better?
Are LLMs different?
Very usable locally assuming you setup your local tooling correctly and you are an actual programmer who can generally help drive this stuff correctly and not just a vibe coder.
I’ve tried multiple that I can run locally and they’re all very much just glorified autocomplete, but slower - on a M4 Max MacBook
I'm using opencode here's one of the projects I've had it complete - just so you know exactly what it's getting done.
I have a large (300,000k loc) sims-like game that I've hand written over last 3 years.
I have a lot of internal administration tooling that has to be built to manage stuff like icons, NPC brain data, world lore, world actions, all kinds of 3d game data, etc, etc.
One example I had qwen do: Work with me to plan out a feature for an admin panel to manage searchable vector embeddings for each NPC's personality, this was around 600 loc across 4 files, back-end database, front-end UI logic, and front-end templating.
It made 3 small mistakes I told it to sort out and fix, which it did.
I essentially let it do it's thing while I was working on main game core coding. So I was pretty hands off and it planned things out nicely before-hand and got my approvals before it built it.
I really wouldn't call it "glorified auto complete"
I do genuinely think that the future is in local models, the online stuff is 100% VC-powered cash market share grabs that will start failing when the forever loop of billions gets disrupted enough.
But at the same time my attemps at comparing claude code + any local model have been such a clear win towards claude I can't bring myself to use a local model seriously just out of ideology.
I also agree the reality is that anthropic/sota models are much faster and much smarter, so if you just want to move fast and have them build for you - I get that these local slow models wouldn't be ideal.
For me, as I said I have a large, super complex primary project that overloads me cognitively, and then backend admin dashboards that are relatively simple and isolated/modular. Just due to this specific project, local/slow models are fine as I just check in every 15-30 mins or whatever and answer any questions they have while I'm focusing on the main project. So basically I just happen to have an ideal scenario/use-case for local models right now.
Oh and I did have to mess around with model settings and stuff to get things to work well. I also started with Cline which sucked badly, and then open code actually had 3 major bugs 5 days ago where it was almost useless in large code bases (e.g. freezing and locking up your project constantly), but they ship multiple updates every day, and those bugs have been resolved. So, it's all definitely moving fast and more for side projects or hobbies rather than production I'd say. Still, I'm quite excited with the progress from a year ago and super hopeful about where it's all headed!
I have a ML Setup with 2 4090 and 128gb of ram, its warm when i use them for finetuning or batch processes.
I do not run them for coding. Its a lot easier and nicer to play around with better models for just 20 $.
[we've hopefully deprovokified the title now]
Why does it bother me so? I have no idea.
i doubt anyone is nouning "agentic" of their own accord (yet)
Pretty much 100% of projects I've done with vibe coding/engineering is in the second category. Stuff I need that either doesn't exist or exists, but is either horribly complex to configure or is a mess of 420 features even though I just need one of them.
It's a lot easier for me to implement that one specific feature just for myself than keep vigilant on an existing app's eventual scope creep as it progresses to the eventual ability to read email[0] =).
[0] http://www.catb.org/jargon/html/Z/Zawinskis-Law.html
Now it is different in a way — I don’t have time to use them.
It is more of a bandwidth thing than need of actual new features. When on daily basis you have 10-20 apps you use for work.