New secret app I built for shipaton is starting to gain traction First milestone reached: $100 MRR I built and released before being invited as a guest judge. Was originally gunning for a few categories but immediately disqualify myself now But… shipaton has a “conflict of interest” category… So there’s still a chance!

Player stats after day 1: 188 total games played 16 escaped (8.5% escape rate) Average time to escape: 16m 20s 5% ran out of time The 100% completion prize has been won The fastest to FULL COMPLETE the game at midnight on 9/9 will get the $1k prize Time to beat: 9m 30s set by Hiếu Trần

The aim was try to trigger the X algorithm to push the game outside my initial feed That hasn’t happened (yet) I’ll be doing a few more hype posts over the next few days leading up to the prize deadline. I also want to add co-op play (originally what I wanted to include in first version). So you can play with friends in the same escape room. Work as a team, etc. being a web game makes it super accessible for friends of all tech levels to connect and play. I think it’s promising. We’ll see if it triggers virality My aim is kinda simple at this stage: try a bunch of things, make a game every week and double down on ones that go viral This game in particular also has some SEO potential. People searching for escape rooms to play online. Theres not a bunch of good ones out there. This one is free, doesn’t need a download, and will have coop. I think it could get some traction. In the initial days of the experiment I got one game concept to go viral (spelling worlds the Roblox alt learning game). But the target market was wrong. No point getting a game to go viral based on an idea that people won’t play. And finally: I’m collecting email signups for each game. So I’m hoping that when one does go viral I’ve got a massive cache of emails to announce a featured game. Like a pay to play type game. Really the business model is evolving and I’m just seeing what works. The answers are becoming clearer with each release. But ultimately I’m enjoying doing something new, creative and learning. So that’s the driving force behind it.

Well, the first person to escape has entered the leaderboard Well done! Nobody has done a FULL CLEAR yet The first to do that gets $100 The fastest to do a FULL CLEAR by 9/9 gets $1000

For those wondering how I made the graphics: It took me 5 days from idea to release Thanks to GPT-5.4 Sol loops. Once I got the prompt working well the loop only took around 12 hours The issue with loops is that they start to regress too quickly. The agent starts to convince itself it's on the right track or takes a bad corner somewhere. To solve this problem I make every iteration a first iteration. So the agent can't convince itself it's doing a good job I call this… a blind loop: How it works: 1. You get nano banana / image gpt or whatever to generate a final version of what you want the mockup to look like 2. You spin up a prompt with a "blind orchestrator" with instructions to spin up blind subagents. Important: the orchestrator never sees the game, never makes an assessment, it leaves this up to the subagents every time. 3. First: you get a blind subagent to compare the final version with your game. Ask it to write a list of the specific things that need fixing "the lighting", "the flooring", "the textures". 4. Then: the orchestrator runs through the list one by one (again this agent never looks at the scene or the game). 5. The orchestrator spins up 3 blind subagents all working in parallel on the same thing. The floor, or the textures, or whatever. 6. When they're done… another subagent is spun up. This one has never talked to any of the other agents and its only job is to assess which version is closest to the final version. I also include the base line too. 7. The winner is selected and the orchestator moves onto the next item to tackle 8. Once it runs through the list it sends it to another blind subagent and compares your game with the final version. It just asks "do these 2 screenshots look like they come from the same game?" 9. Rinse and repeat 10. Once you have the version you like now it's your job to make it run smoothly by optimising, optimising and optimising.

Majority of my time was spent optimising @threejs for the browser Did occur to me that using a proper game engine like Unreal might be fun though But first step is learning the ropes and getting one of these games to go viral Once viral I'll have a marketing list to promote a paid game in future

Ultracode has changed my opinion on Opus It's a chatty model but it gets stuff done atleast Yes, it burns a lot of tokens in the process. But those tokens seem to be a lot cheaper than fable.

The main support issue I receive is people being unable to link their DataForSEO account correctly It looks like they have some sort of delay (by a day or two) until the api key you sign up for even works I'm tempted to add a monthly plan that uses my DataForSEO account (onsells it). But I don't know if it's worth it.