Google Playground: Create and play custom games (blog.google)

97 pointsby acossta10 hours ago181 comments
https://labs.google/playground

xnx 9 hours ago

Just got #2 in the world (for now) on "Steampunk Match". Very impressive what's possible in the browser. No way I would've thought this was AI generated. It was much higher quality than the vibe coded games out of Claude. The best outcome would be for this to enable some new weird games that wouldn't have gotten made otherwise, and also to bankrupt games that basically operate as casinos.

jenniferhooley 8 hours ago

No, this is exactly what Claude vibe codes, this is definitely a one-shot Claude style game (assuming it looks up a decent pixel art pack). LLMs are pretty decent these days at making standard game clones like this, you just have to add a system prompt about making it look like a real indie-style pixel art game instead of just letting it make it's standard "web game" style. I assume google has a good background system prompt/harness to do this automatically.

zamadatix 8 hours ago

This played waaaay better than a one-shot Claude style game but I'm sure it was not one-shot either.

sporadicallyjoe 6 hours ago

Just got #1. The next match will always be highlighted when time is running low. I never ran out of options. The game is fun, but it definitely seems as though there's still room for improvement.

xnx 5 hours ago

Agree. The game has a good amount of "juice" (https://garden.bradwoods.io/notes/design/juice), but not as much as the hyper=optimized AAA(?) casual games.

Sarkie an hour ago

Reloads the same page for me

pkal 5 hours ago

I don't want to (and can't) use this myself, but I've always wanted to see if an AI could implement an idea I had for a while: "A 4D version of Agar.io where you move through a 3D slice of space by moving the mouse cursor, and then rotate through the fourth dimension using the scroll wheel. All other game principles remain the same." Will this implement support for multi-player games as well? The really interesting part here for me is how well the AI will implement a game unconventional UI and how successful it is at making it usable and intuitive for humans.

palata 26 minutes ago

I thought it was just not working on Firefox, but it doesn't seem to work for me on Google Chrome.

"Create custom games in minutes > Press Start" just opens a new tab with... the same page?

OsrsNeedsf2P 7 hours ago

We've hosted an AI game development platform for a while now and found there's a big difference between "making a game" and "making a fun game". I'd love to see if they are solving the real problem, but the link to try it out is a 403 for me.

CuriouslyC 7 hours ago

I don't think AI will ever really solve "making a fun game" because:

1. Games are highly complex systems, so for example adding a fun mechanic from one game to another game can actually make that game less fun, and AI has no way to know, you just have to playtest it.

2. Games are evergreen (people still play and love the original Zelda/Mario/Tetris) and social (you want to share your love of game XYZ with others), so there's literally no reason for anyone to play a purely derivative game, when you can just play the original.

Eventually AI will be able to make perfect assets and all the other stuff AROUND making a fun game, but the game design will always be a human thing. At best, AI will come up with a bunch of game design experiments that a human will need to playtest and provide feedback on.

icantevenhold 7 hours ago

That’s fine though?

I’m having a lot of fun creating an “improved” clone of a very old school game I loved.

It takes lots of back and forth but there is definitely (for me at least) to play this derivative game since it adds a lot of levels and stuff that weren’t available in the original.

Without AI I wouldn’t be able to do anything; but with it it can make some changes, I test them and we iterate on it.

So for me AI solves “making a fun game”. It doesn’t “one shot GTA7” if that is your goal but that also sounds boring

monknomo 7 hours ago

this is probably a personal problem, but sometimes I get turned around on 'fun making a game' vs 'making a fun game' and I have the idea that ai elides this distinction even further

CuriouslyC 7 hours ago

You misunderstand me, AI solves the "making" part, but not the "fun" part, which is 100% you.

Culonavirus 7 hours ago

Yea not the "making" part even (at least not yet). Every single demo/sample of a vibecoded* game thing is a piss poor "counter strike clone" or "gta clone" type of app that has bare bones everything (and i mean PS2 level or worse) and plays like absolute ass down to the basics of character control ans basic gameplay mechanics.

*: I don't consider a project you built with an LLM to be "vibecoded" if all the important ideas are from your head, you know what the code is supposed to be doing (domain model is in your head) and you guided the project every step of the way. Otherwise we're all vibecode. So yea, I don't doubt you can create amazing games with AI, but "with" as in "together", not as in "Claude, build me a Minecraft clone, make it fun, no mistakes."

TomGarden 6 hours ago

You may be right, at the same time a lot of "AI will never solve X" takes have aged pretty poorly, and I'm not confident what's fun about existing games cannot be codified and shown statistically somehow. Some genres seem more accessible to AI than others

CuriouslyC 6 hours ago

It's hard to say for sure, I think we can at least confidently assert that games are going to be more challenging than other forms of creative expression like Books, Music, Art, etc because people's tolerance for derivative games is lower than their tolerance for derivative movies/music.

TomGarden 5 hours ago

Agreed!

And I genuinely hope there will be some categories of games/music/books/art where human input is still needed and preferred. Currently I'm already a handful of bulletpoints down on the list of stuff I thought AI would never be able to do, and it's been kind of destabilizing

jpalawaga 6 hours ago

i think the difference here is that humans can't even write down what makes a great game great. we don't know. you have to play it.

if we can't even write it down, how is an llm going to be able to ace it?

s0ss 6 hours ago

I don't think anyone, given better alternatives, would choose games like these. There's a reason low effort output of LLMs has been dubbed Slop... Slop isn't fun or interesting to consume.

nekooooo 5 hours ago

seriously, games require balance and playtesting, and synthetic users don't count.

advisedwang 6 hours ago

AI will solve it the same way it solves everything else - by reproducing the patterns in its source data. Which means you will never see novel mechanics or combinations or mechanics.

joquarky 2 hours ago

"Never" is a very long time.

aqme28 9 hours ago

How long until someone makes a tiktok-style game platform?

Play a little game, then when you're done it generates a new one based on what you've enjoyed. Repeat ad infinitum.

rationalist 8 hours ago

Thanks for giving people (or an AI scraping this), the idea :-/

regenschutz 8 hours ago

Environmental impact aside, that seems way less harmful than TikTok, though. You'll probably play the average game for longer than you watch the average TikTok video, meaning that your attention span won't be that bad.

You also have to actively use your game for most games, unlike TikTok videos which you can just watch with your brain turned off.

aqme28 8 hours ago

I'm not the first one to have this one for sure. I would have started working on this if not for the small problem of finding it unethical to build :(

Permik 8 hours ago

Technically there is already one, it's called HypeHype, but it's using their in-house graph-style editor. Vendor-lock-in out the whazoo.

Haven't followed them too closely, but wouldn't be surprised if they'd added LLM tools to the platform.

glenstein 8 hours ago

>How long until someone makes a tiktok-style game platform?

Well to your point, youtube already has these little mini games that exist in portrait mode. Seems like something is liminally out there pointing in that direction.

alach11 7 hours ago

This is a really neat idea to explore, but I feel like it would be hard to succeed. Games require a very different level of engagement from the audience, with some effort to learn the mechanics or understand what to do next. Short-form video seems like the complete opposite... totally relaxed consumption.

aroman 7 hours ago

This very idea has been tried - and venture funded - to the tune of many millions of dollars every 6 months for the past 4 years.

The last few founders I knew working on variations of the idea finally pivoted out over the summer. It’s definitely one of those ideas that sounds great until you try building it and you realize there’s nothing there. Definitely will get funded again before the year is up!

xnx 7 hours ago

Has anyone made a generative version of TikTok yet? I suppose that's already what TikTok is, but with a slow feedback loop and tricky filters against AI generated content.

hmokiguess 8 hours ago

I'm okay with Google offering models, but I'm not okay with Google offering more PaaS offerings.

Let developers use your models and tools and build stuff with it. Why own everything.

Google has too much already and in my opinion they have no business owning a gaming platform.

pjmlp 8 hours ago

Because many devs don't pay for tools unless forced otherwise via a network paywall.

bko 8 hours ago

I don't know, it seems like it's just fun thing to play around with. I don't think serious things are meant to be built on this.

I often want to play simple games like Pacman, space invader, breakout, tetris or some other random iteration. Sometimes there are non-spammy simple versions of this game but often there aren't. This seems like a pretty cool fix. And if they disappear in the future, who cares?

hmokiguess 7 hours ago

That's precisely how something ends up becoming ubiquitous. You, and everyone else, start having fun on it and then suddenly it's a locked-in platform monetized by them.

YouTube started exactly how you described it, some silly thing not meant to be serious and today powers multiple 100M+ businesses using it for content to reach mass audiences.

xnx 7 hours ago

> I don't think serious things are meant to be built on this.

I read at some point that projects at Google didn't get a greenlight unless there was a reasonable expectation they could be used directly or indirectly by a billion people.

yipinwong 7 hours ago

With your logic, Google should give us their search logic/libraries, so we can build our own search engines.

You ain't making sense. Companies need $, and what's wrong with what they do with what they own and can do in this particular case?

underlipton 6 hours ago

>With your logic, Google should give us their search logic/libraries, so we can build our own search engines.

Yes. Google does not actually care about search anymore, and the threat that the technology could disappear altogether is real.

yipinwong 6 hours ago

That's a slippery slope. It's like saying, we should not drive cars because it kills people.

underlipton 4 hours ago

My first read is that that's a terrible analogy, but also...

hmokiguess 6 hours ago

Nothing wrong with me having an opinion on their strategy

My logic is not “don’t make money” but more so pick a lane

They can empower the community and let a PaaS emerge that’s locked in on their APIs for example

For example, did Shopify get into building Marketplaces for E-commerce? No

It isn’t like they would not be able to make money from the gaming industry by being just the layer zero, my beef here is that they’re going one layer up

yipinwong 5 hours ago

I respect the opinions, and I was looking for more logical reasoning on how one arrives at that.

Whether to empower the company or not via open-source/open-weight etc is based on a company culture, value, and future direction/projection.

And it all depends on the scale.

Google didn't need no HR, no companies normally start with everything in place. AS the companies scale up, they add security team, HR, legal team, etc.

That means more $. Google is 20x the size of Shopify in terms of market cap. Google was loved for their search engines when it was at shopify level initially. REmember decades ago when everyone loved Google search?

This does not mean, Google will keep the same strategies for their direction neither will Shopify. I already hear a lot of complaints from my friends hosting on Shopify on the enshitification.

Anyways, I diregress a bit.

So my point is, at least try to reason about why `hmokiguess` arrived at "Google has too much already and in my opinion they have no business owning a gaming platform". What is too much here in homikiguess's opinion (that is verys subjective, need verification),

hmokiguess 2 hours ago

Where did you get open-source/open-weight from my message? They offer models via APIs, they have GCP, they already have a Cloud PaaS that lets you build a Gaming PaaS on top (in fact, some existing ones are exactly that)

You're contradicting yourself, the reasoning for them to have too much was said by you in your own comment, they are 20x the size of Shopify.

Kkoala 7 hours ago

Points to https://playground.google/ which just returns 403 error. Cool

icantevenhold 7 hours ago

“you do not have access to this document. That’s all we know.”

Well ok then

accidc 6 hours ago

They definitely know why, otherwise they wouldn’t be able to tell who to 403 vs not. They obviously dont care to tell you because of ‘security’.

This dismissive contemptuous attitude is typical of all big tech, all your value is just reduced to data generator to be mined, without any other regard.

tgma 4 hours ago

It looks like the generic edge server 403ing (presumably country-gated), not the application generating that error message deliberately.

gulmothrowaway 7 hours ago

https://killedbygoogle.com/

TomGarden 7 hours ago

For anyone getting a 403, it's US only right now and fails rather ungracefully. I just tried out a few games, framerates where strange/choppy, even in a match 3 game, and the games I tried were quite bad overall. I'm sure this type of thing will get good very soon though

Leynos 7 hours ago

Google yet again showing their leadership in product delivery, marketing strategy and bureaucracy

throwaway314155 6 hours ago

Getting a 403 in the US.

porridgeraisin 6 hours ago

Works in india

msabalau 8 hours ago

You can build standard games now, and there is a waitlist for Unity Spark. But there are demos of Unity Spark games now, if you want to see what will be possible.

I was able to spin up a couple of games really quickly--a 2D cosy space exploration game, and a snarky sci fi trivia game. I'd say the the writting for the humorous trivia questions and the cosy interactions was reasonable--this isn't a tool that can only do reskins of old school arcade games. In addition to music and graphics it can do text to speech.

It's still an experiment, simultaneous impressive, and frustrating, with rather unexpectedly low prompt compliance. But, beta.

It really doesn't seem to like shifting from multiplayer to solo play. It seems like you ought to have a strong opinion upfront. (again, early days)

It's natural to think of this quick and easy tool for playing game, but I suspect part of the eventual value will be learning tools and "self gamification" I could imagine doing a variant of my trivial game for memorization or language learning.

mycocola 5 hours ago

Hard for me to understand the why in this. I don’t think tech companies have ever understood games, almost certainly because they do not engage with games.

Edit: It’s for training. RL on playtimes, ideas, etc. Just rushing towards a world where we have no value to each other.

_pdp_ 6 hours ago

I could not test it because I am also facing 403 error - UK.

Anyway...

If you are interested, there is also an open-source way to do exactly this and it works with your existing subscriptions and local models too - your data is kept private on your devices.

You can make the game, stream it directly from your AI hub or play it locally on your devices. You can cast it on the TV while converting your phone into a controller (with haptics support) or you can connect physical game controllers for local co-op.

https://github.com/pdparchitect/noodle

The README does not talk about this feature but you can find videos in my twitter account.

rakamotog 5 hours ago

I just wish, someone tested this experience for EU where it doesnt work. Auto playing video below the fold and try plays video in a new tab.

shooly 4 hours ago

Off-topic, but that showcase image in this repo is truly pathetic. "What should I get Mum?", "find me something to do on Sunday morning" - is this seriously what people need AI for now?

danvoell 8 hours ago

Best case scenario for this is...replace Roblox with games that don't have reward systems solely based on you playing as long as possible. We are losing a generation of children to these games.

stephenlf 8 hours ago

I predict a very orthogonal outcome. This is an interesting experiment. If it gains some traction, Roblox and Minecraft are both very well situated to build a similar product and dominate the market.

hmokiguess 8 hours ago

If anything, this is them trying to eat their lunch by grabbing the market share and using the same playbook.

Do you really think Google cares about gameplay in the same likes of, say, Nintendo?

zamadatix 8 hours ago

I don't think Google gives a crap about games one way or the other, they just want people to use their AI.

geraldwhen 7 hours ago

If that were true, they would release Gemini 4.

zamadatix 2 hours ago

I'm sure they will right after their initial "cyberdefenders" have had a few weeks to hype how it's too powerful to release.

estearum 7 hours ago

Having been a young game-addicted person in the past, I would assume the addictive part of Roblox is the social component, no?

Is it really just that they give kids nice shiny imaginary points for playing longer?

watwut 6 hours ago

Kids I know genuinely liked playing Roblox games. It was not just shiny imaginary points, it was that games were "for them" and they did not needed money to try another one.

MisterMunchkin 4 hours ago

Yeah the addictive part is being richer than the other children. It’s like trading card games, the actual game isn’t good but you get to be better than the people who don’t have rich parents.

estearum 3 hours ago

Hm... I remember games (especially social ones) being plenty addictive even without dynamics like that.

watwut 6 hours ago

Who is it "we" that is loosing a generation of children and for what purpose are those people loosing them?

regenschutz 8 hours ago

I've always found Google Slides to be a great way to create cute, personal games. It requires no coding, and anyone can play them easily in their browser. Seeing what people are able to do with a simple presentation (PowerPoint, if you will) has been repeatedly eye-opening every time I've seen one.

I'm a bit worried that Google Slides-games will fall out of fashion now ;(

d-lowl 8 hours ago

Tangentially related, have a look at Downpour, you might like it, if you like making ppt games! https://downpour.games/

xnx 7 hours ago

Never heard of this. Is there an example of the best of the genre? I assume these are point-and-click adventures?

vmg12 8 hours ago

If you want to try this but with free multiplayer servers check out https://snack.game (my site)

I also didn't bother with in-app game dev for now since I figured your local agents will be better. So for now you just develop locally with a CLI and your favorite subsidized model.

light_triad 6 hours ago

The biggest challenge is designing the mechanics that make games fun. AI is not quite there yet but with enough data could potentially get there.

I put together a site a few months back to play around with 3d assets from Sketchfab and animated characters from Mixamo as an experiment: https://gobananas.co/

goshx 7 hours ago

Beware: "you are on the list" - "or upgrade to access instantly"

I upgraded, same message. I downgraded, they kept the money because now I have a month of a plan that I didn't need to check something I still don't have access to.

qingcharles 6 hours ago

The games on here were really janky.

The Sandbox one is a lot more mature and better thought out:

https://www.sandbox.game/en/

ragazzina 8 hours ago

Since this thread will contain the intersection of people interested in coding games and people interested in AI, can I ask whether the latest AI coding tools can help someone vibe code a simple low-poly 3D game? I only ever used Twine before.

gobdovan 8 hours ago

Yep. Simplest is browser game with three.js, the only lib you need. But for low-poly 3D, you can basically tell the frontier LLMs to build yourself the rasteriser itself in whatever language you want (not recommending it, just saying they're that good). Literally just put your comment into Claude Code or Codex and see it do it.

NiceWayToDoIT 7 hours ago

So, google invented idea collection box for their own profit? Again?

niwtsol 7 hours ago

A few of my friends and I have been building a game for a few weeks. It has been really fun because anyone can make a level and it’s somewhat random what level you get sent to- each level could have wildly different controls/goals, but getting oriented is part of the fun. We also have a ton of inside jokes and memories cooked in - I don’t think it would be very fun for someone external, it’s fun because a group of friends are building something together and that process is very fun. This seems to be just more of a game printing machine

kursus 6 hours ago

I don't see the appeal of scrolling through a list of games I could potentially make myself VS scrolling through a list of games I could immediately play.

xnx 6 hours ago

? You can immediately play the games on that page.

jameshart 7 hours ago

Does Google not have lawyers any more? Playground Games is the name of the Microsoft-owned games studio behind Forza Horizon; X-Box studio is as part of their current restructuring merging them with Turn 10 (the mainline Forza studio) and, weirdly, handing the resulting studio Fable to work on, but Microsoft definitely still has an interest in the trademark of ‘playground’ in the context of video games.

TheAceOfHearts 5 hours ago

It doesn't work for me, when I click any of the links it just opens a new tab to the same page. $4.2 Trillion marketcap company with access to world class geniuses plus effectively unlimited AI compute and this is the trash they're making.

educar 8 hours ago

I got a 403 from Germany

giarc 8 hours ago

For the main page or for the playground.google link?

calgoo 7 hours ago

playground.google link

calgoo 7 hours ago

Same in Spain...

sha-3 7 hours ago

> Playground launches today for users in the U.S. (18+) at playground.google, with tiered creation access rolling out based on your Google One membership.

Looks like they forgot to create a "Not available in your region" page, which makes me wonder whether they made this over a weekend.