Coolify users, be careful out there
Just added smart hints to my GobNative engine for the 1991 classic Gobliiins! 🧙
I always loved these games, but some puzzles were ridiculously hard. Now the game tracks your progress and gives you little hints when you're stuck, without spoiling the fun!
games.encrypted-cat.com/devl…
AI slop is delegating the vision.
AI-assisted work is delegating the execution.
Slop: "Hey Suno, make me a cool electronic track."
The model picks the composition, arrangement, mix, and vocals. Your only decision was "cool."
Assisted: "Here's Strudel, where music is code. 128 BPM, F# minor, four-on-the-floor kick, syncopated bass, open the filter slowly, second synth at bar 32."
Now every choice is mine, and the output is something I can read, change, and iterate on.
Same AI. The difference is whether you showed up with decisions or just a wish.
I built my own engine for a one-hour horror game on top of @threejs.
Probably overkill 😅 But now 70 sequences, 116 interactables, dialogue, scares, puzzles, and enemy encounters all live in data.
The engine knows how to be scary. The story just tells it what to be scared of.
Wrote about how it works 👇
0xkot.itch.io/the-cradle-epi…
#threejs #gamedev #indiedev
Really enjoyed the demo! It has that classic old-school Final Fantasy feeling I’ve missed. The battles, magic, summons… it just hits right. Can’t wait for the full release!
My biggest issue with Gemini models has never really been capability, it’s the false-positive refusals. I’ve had completely legitimate prompts get blocked or the model simply refuse to do what I asked. I rarely run into that with Anthropic or OpenAI models. Hopefully this generation improves that, because otherwise it sounds very promising.
Gemini 4 is finally here! unexpectedly google’s actually released a good model:
- sets a new record on coding (deepSWE 1.1)
- goes head-to-head with Gpt 6 and opus 5.5
- their best reasoning model to-date (gemini historically sucked at this)
where it falls short - doesn’t seem to be “best” at anything. it’s a good catchup model but not putting them at #1
but first model since demis stepped down not bad!
Same goes for software.
At some point, paying $20–50/month for every tool stops making sense when you can just build your own stack, own the whole thing, and change anything you want.
As long as your hardware can run it, the cost of custom software is heading toward zero.
Tried it on my horror game The Cradle and ended up re-voicing the whole thing.
v3 vs v4 Turbo, same scene 👇 Headphones on.
Introducing Eleven v4 and Eleven v4 Turbo, our fastest and most emotive voice models yet.
Ranked #1 by Artificial Analysis.
Finding beta testers is hard. Seeing how a real player actually behaves is even harder.
Today I uploaded my game to @itchio, sent it to a small Twitch horror streamer with ~10 viewers, and donated for him to play it blind.
He finished it. I found several bugs. He got unique content.
Super easy distribution, real-world testing, everyone wins.














