Kiddow

@AIWarper Ty, glad you liked :)

@kiddowdev Agreed Btw this is dope

Anyone who’s actually tried building even a simple game jam prototype knows it’s barely about AI coding ability. It comes down to having a strong idea and good taste. Most people have neither of these, hence all these Codex game demos posts popping up. 99.9% junk

@MrReche Played it for a bit and got strong Breathedge vibes. Leaning into that direction with survival systems like food and water plus upgrades tied to them could fit really well

I enjoyed so much working in my #vibejam game Off-G Overtime that I'd like to expand it into a proper game. I'd love to hear your ideas of how could I properly develop it into a full-fledged system with clear goals. Would you play a game like this? what would to do to improve it?

I've been doing traditional game jams for a long time and jam games are always simpler by nature, but the quality here genuinely surprised me. I avoided Three.js going in because of the graphic and optimization limitations, but after playing entries like @leocooout capybara game and @DannyLimanseta Tiny Skies, I completely changed my mind. And I wouldn't call that kind of work slop by any stretch. Excited for next year, I think it's going to be a real reference point for how much the barrier to entry in game dev has dropped

For the second year, @levelsio has organized the Vibe Jam, and I am jury. I think what he's doing is important: 1. Games are intricate software puzzles with the multiplicative complexity of hardcore engineering x creative problems. 2. While AI is now incredibly helpful in most disciplines like legal, programming, healthcare, maths, chemistry, and physics, they aren't great for large creative problems like making games yet. 3. Which is why I think the Vibe Jam is becoming an important yearly benchmark to appreciate progress in the field. Each game submitted has to be 90% AI. 4. Yes, don't expect masterpieces, it's still slop & very far from what gamedevs currently achieve, and that's the point: to measure the trajectory of this tech & the growing accessibility of games development. It's my way of staying ahead of the curve, and particularly relevant to my work, The Last Night (@TLN_Game).

@s13k_ I refuse to fix my spinning suicidal frog, it's an intended feature for sure

Shipped an update to the award generator for #vibejam Give your game the ridiculous palm award it deserves 🏆 award-generator.s13k.dev

@HLS_dev Finally a game to scratch my itch for riding giant rats🤣 Nice work man, can't imagine how hellish it was to implement systems like this on a tight jam schedule

Trailer for my #vibejam game. Audio on! Try it -> vibe-jam-survival.vercel.app #gamedev #indiegame #survivalGame #threejs

@andreeliasdev That's the lesson I'm taking into the next one, my codebase got messy enough that I'm still untangling it now

@kiddowdev This is simply a game changer to be honest. If the document is good you can ask it both for generating the code and code review (to make sure it's being followed). And the best part is that you can modify and extend it as you want

I've built a multiplayer survival game for the browser in 30 days and I didnt write a single line of code 🤯 So I'd like to write my notes about it once the deadline is done now. The last 20% of a project is indeed the hardest part of it all. In the last 2 days i've been working on the final version of Hollowlands for @levelsio's 2026 #vibejam I worked a lot! I fixed a lot of bugs, tested a lot playing with my wife. Fixed more bugs... But now, thank God, I have the final result! The game looks good, yes. I've spent half of the jam just tweaking every single detail of the procedural world generation. And It was worth it! The game still runs well on most devices and still has less than 20MB in size. Which is pretty impressive to me. The process of building was very straighforward: 1. I used @threejs + React to create the game. Before I started I created a huge document defining every rule i'd like the codebase to be implemented upon. It had clean code rules, archtecture decisions, ECS principles (good for games), and so on. This helped a lot constrain the AI to maintain the code maintainable and separated into clear domains (systems). This document was made partially by me given my previous experience building web games (I've made a lot of mistakes in the past and made sure they will not repeat again) and partially AI suggesting best practices. 2. For every feature I prompted the AI, I was very specific on details that I'd like implemented. If I knew what I was doing, I was more specific on the "how" I wanted to be done. If I didnt know what was doing I first asked the AI to brainstorm possibilities with me, based on industry standards, pros and cons, and so on. Then I would decide what path to go. 3. Every single feature I used Leva for tweaking the values. So for example, the size of the trees, colors, distance between objects, animation speed, etc. Everything I have a slider that I can adjust. 4. To make the game look good I used @tripoai to create the models. To be honest it's not 100% perfect. If you check the character in game you can notice a few issues here and there (the arms lol), but I believe that it will keep getting better over time. 1 Year ago I tried and it wasnt even close to what it's now. Then I used a few post-processing + shaders + particles techniques to bring the "wow" factor. 5. I did only 1 feature at a time. And every change it was a commit with a clear message of what was done. This helped the AI fetch previous commit to understand what changed and know exactly what happened in the past. If I opened multiple terminals at once and blasted prompts the code and commit history would be a mess in a few days. And for every change the AI did, I asked it to do a Code Review of everything that was changed and look for violations on the document I wrote in the beggining defining the codebase guidelines. I realized that I pretty much applied software engineer principles using AI: Code, review and merge, code, review and merge... 6. On the last week I implemented the multiplayer using @colyseus which was pretty nice. I used AI to fetch the whole documentation and create a skill.md file that helped a lot. The creator of the framework @endel also did a extensive research on how real multiplayer games are implemented. It's open source and it was a gold mine for the AI to come up with the implementation for my game. You can ask him the link :) And that was it I think. I'm extremely tired now. The last 2 days was insane. The game's final version is not what I had in mind in the beginning of the jam. I had to cut a lot of cool features. But given the 30 days deadline I think it was a huge success. Hands down my best game ever made. Now I'll take a few days to rest and come back with more updates on the game. Maybe it can become a big deal in the future with more updates. Who knows. And in the event I win first place in this game jam, I'll use the money to fund my own game studio + cover the expenses of my child that is going to be born in September :) Cheers guys! If you have any question, feel free to reach out. I'll answer every non-bot comment in here haha Note: The link to play is in my profile

Nice cost breakdown. Mine came out to around $65 total. $30 Glif subscription + $10 extra credits for art and audio, $5 TripoAI for 3D assets, $20 Cursor. @heyglif surprised me, I could generate an enemy image and use it as context to generate matching sounds for it. Cursor held up well too, managed to finish the whole game on their cheapest plan

Ok, #vibejam is over, and here's a video of my submission, Tron: Light Cycles. Built on @cursor_ai with @threejs. Play it here: tron.ganji.me It was a fun experience overall and I learned a bunch of things. Thanks to @levelsio for organizing it. Costs breakdown: - @cursor_ai's $60 subscription and $30 extra usage. Tried to use it economically and default to composer 2, only switched to frontier models for complex problems. - Used @ElevenLabs for the background music, got the creator subscription for $22 which was unnecessary, could've used the $5 account instead. - @veedstudio account $30 for editing a social media video. There may be cheaper ways, but this was my first experience editing a video ever and they have quite a simple interface for it. Total: $142 and around 14 days of working on it. My experience with what each model does best: - Gemini 3.1 pro was best at creating the 3d models in the game - Composer 2 is fast and cheap, so food for quick iterations on small stuff and additions when you know what you want. - GPT 5.5 did the heavy lifting in a lot of the more complex features, level editor, graphics, animations, etc. - Opus 4.7 was my alternate choice when got frustrated with GPT 5.5, generally better at tasks that need a lot of research and digging into the code before building. - Used Grok 4.20 for enemy AI logic, worked better than all other models.

@AriescarTu Watching it go from nothing to where it got is genuinely impressive

#vibejam breakdown 02 Built an exploration game Zero to playable Here's what I did in 20 days. Modular Avatar System Infinite Chunk System Erosion & Reveal System Combat & Boss System Crystal Vein System Weather System Dialogue System Audio System Radio System UI / HUD / Filter System Async Multiplayer & Cloud Sync System IDLE System #gamedev #vibecoding #threejs

@rrmdp Hinom tower submitted🫡! hinomtower.xyz

COME ON! do like Daniel: submit your vibe-coded game (It's free) I'm building a directory 1️⃣8️⃣0️⃣ already in the list BTW, did you join the 2026 #vibejam?

@TheJohnnyStaley @JoshRozin For me, game feel and asset consistency. If hitting something feels like nothing or the art style is all over the place, it breaks the whole experience regardless of how technically impressive it is

@JoshRozin what would make you consider a vibe-coded game slop?

As someone who makes a non-vibe coded game with many real users, a lot of the entries are genuinely impressive and not slop. The technical aspect of building software now takes 25-50% of the effort as it did 4 years ago. Once you get over the initial hurdle of understanding software, the hard part isn't necessarily building the software, it's the architecture, product, business and, in larger companies, company political conflicts that make it hard. Those who have been in software pre-AI know this well and which is why it's always encouraged to get your product in front of people so that you can start solving those problems. Those conflicts will be an excellent frontier to solve next.

@JoshRozin As someone who's been building games for a while, the code was never really the hard part. Knowing what to build and how always was. But technical effort dropping this much this fast is still kind of insane to watch

@imkieransmith this is giving me some strong Karlson vibes, love it

Just over 24 hours until the end of #vibejam! Today I'm showing off destructible doors, bullet time slo-mo, and parkour killing fun.

@adrscott @levelsio @cursor_ai @tripoai Played it for a bit, good work on this. The screenshake and impact on hits really feels good

Here’s my submission for the #vibejam @levelsio @cursor_ai @tripoai contest: AniKombat. AniKombat is a browser-based 3D fighting game built with Three.js. It has combos, instant VS CPU matches, training mode, casual online multiplayer, and ranked ladder play. No login or signup is required to play. You can jump straight into Training, VS CPU, or casual online matches as a guest. Accounts are optional and only used for ranked progression, match history, and ladder climbing. I built this in about 2-3 weeks using AI tools: - @cursor_ai and @OpenAI with GPT-5.4/5 for coding - @threejs for the 3D game client - @tripoai for 3D model assets - @ElevenLabs for sound effects/music - GPT Image for artwork, UI direction, and visual planning . This was a great learning experience. The hardest part was definitely online networking: sync, interpolation, prediction, reconciliation, and making combat feel playable over latency.

@levelsio @cursor_ai @boltdotnew @heyglif @tripoai Submitted Hinom Tower earlier today, fast FPS multiplayer and kind of messy in the best way would love to hear your thoughts

@levelsio @cursor_ai @boltdotnew @heyglif @tripoai Play it here: hinomtower.xyz

🧑‍🚀 Day 28 of the @cursor_ai #vibejam Proudly sponsored by @cursor_ai + @boltdotnew + @heyglif + @tripoai Prizes to win (submit your vibe coded game before May 1!) 🏆 $25,000 🥈 $10,000 🥉 $5,000 🚨 LAST DAY TO SUBMIT! 🤯 The deadline is May 1 at 13:37 (LEET TIME) in UTC, so about 13.5 hours from now, there's $40,000 in prizes so why not try vibecode one in the next few hours? 😂 My favorite games from today: 🏜️ Eyrie by @slowchaz 🐓 Coop-Strike @mayfer 🗻 Mountain Adventure by @asalinasmark 🤺 AniKombat by @adrscott 📊 Mini stats: 674 games submitted 210,542 players 12,413,875 views Reply in this thread with updates on your current games to share your progress, and add tag #vibejam so I see and can include you in the daily tweet Wanna to participate? You can still start now and submit your game any time before May 1! (we started April 1 btw) There's now $40,000 in prizes for you to win, see threads below for more info. The Gold prize is $25,000, silver is $10,000 and bronze is $5,000!