Robotopia: A 3D, first-person, talking simulator • Hacker News Board

Re: Robotopia: A 3D, first-person, talking simulator

#11

Post by tom_0 » Sat, Jan 10, 2026, 4:29 AM UTC

Scaevolus wrote: post #10

tom_0 wrote: post #6

Hey, Tommaso here, I'm one of the founders of the Robotopia studio. I didn't expect to see this here! Ask me anything :)

Are the LLMs run on-device, or does this use cloud compute? (Off-topic AMA question: Did you see my voxel grid visibility post?)

The "big" one is Llama3.3-70b on the cloud, right now. On GroqCloud in fact, but we have a cloud router that gives us several backups if Groq abandoned us.

We use a ton of smaller models (embeddings, vibe checks, TTS, ASR, etc) and if we had enough scale we'll try to run those locally for users that have big enough GPUs.

(You mean the voxel grid visibility from 2014?! I'm sure I did at the time... but I left MC in 2020 so don't even remember my own algorithm right now)

Re: Robotopia: A 3D, first-person, talking simulator

#12

Post by Scaevolus » Sat, Jan 10, 2026, 4:57 AM UTC

tom_0 wrote: post #11

Scaevolus wrote: post #10

Earlier quoted context omitted.

Are the LLMs run on-device, or does this use cloud compute? (Off-topic AMA question: Did you see my voxel grid visibility post?)

The "big" one is Llama3.3-70b on the cloud, right now. On GroqCloud in fact, but we have a cloud router that gives us several backups if Groq abandoned us. We use a ton of smaller models (embeddings, vibe checks, TTS, ASR, etc) and if we had enough scale we'll try to run those locally for users that have big enough GPUs. (You mean the voxel grid visibility from 2014?! I'm sure I did at the time... but I left MC in 20…

Shipping GPU-accelerated ML models in games looks difficult, are there any major examples other than vendor-locked upscaling like DLSS or FSR?

(Yep! https://cod.ifies.com/voxel-visibility/ )

Re: Robotopia: A 3D, first-person, talking simulator

#13

Post by Charmunk » Sat, Jan 10, 2026, 5:23 AM UTC

tom_0 wrote: post #6

Hey, Tommaso here, I'm one of the founders of the Robotopia studio. I didn't expect to see this here! Ask me anything :)

Hey! Robotopia looks awesome, I'm excited to try it out when it launches. How do you convert the LLM output to actions? Is there more broad actions available (ie like creating any object, moving anything anywhere) exposed to the LLM or is it more specific tools it can call?

Re: Robotopia: A 3D, first-person, talking simulator

#14

Post by tom_0 » Sat, Jan 10, 2026, 5:25 AM UTC

Scaevolus wrote: post #12

tom_0 wrote: post #11

Earlier quoted context omitted.

The "big" one is Llama3.3-70b on the cloud, right now. On GroqCloud in fact, but we have a cloud router that gives us several backups if Groq abandoned us. We use a ton of smaller models (embeddings, vibe checks, TTS, ASR, etc) and if we had enough scale we'll try to run those locally for users that have big enough GPUs. (You mean the voxel grid visibility from 2014?! I'm sure I did at the time... but I left MC in 20…

Shipping GPU-accelerated ML models in games looks difficult, are there any major examples other than vendor-locked upscaling like DLSS or FSR? (Yep! https://cod.ifies.com/voxel-visibility/ )

Yeah it's extremely difficult right now, especially for a Windows game that can't have players install Pytorch and the Cuda Toolkit!

ONNX and DirectML seem sort of promising right now, but it's all super raw. Even if that worked, local models are bottlenecked by VRAM and that's never been more expensive. And we need to fit 6gb of game in there as well. Even if _that_ worked, we'd need to timeslice the compute inside the frame so that the game doesn't hang for 1 second. And then we'd get to fight every driver in existence :) Basically it's just not possible unless you have a full-time expert dedicated to this IMO. Maybe it'll change!

About the voxel visibility: yeah that was awesome, I remember :) Long story short MC is CPU-bound and the frustum clippings' CPU cost didn't get paid off by the reduced overdraw, so it wasn't worth it. Then a guy called Jonathan Hoof rewrote the entire thing to be separated in a 360° scan done on another thread when you changed chunk + a in-frustum walk that worked completely differently, and I don't remember the details but it did fix the ravine issue entirely!

Re: Robotopia: A 3D, first-person, talking simulator

#15

Post by shminkle » Sat, Jan 10, 2026, 5:29 AM UTC

lifetimerubyist wrote: post #5

Another game that has LLM powered NPCs is the f2p action game from China called "Where Winds Meet" and players came up with all sorts of hilarious ways to cheat quests and other fun stuff via prompt injections. https://www.dexerto.com/gaming/where-winds-meet-players-are-... https://www.rockpapershotgun.com/where-winds-meet-player-con...

I had no idea this game had LLM NPCs. Interesting

Re: Robotopia: A 3D, first-person, talking simulator

#16

Post by shminkle » Sat, Jan 10, 2026, 5:30 AM UTC

psawaya wrote: post #7

fosterfriends wrote: post #3

I’m so excited to see LLMs used more creatively in video games. So many new mechanics can be unlocked with LLMs as judges

Agreed! Some other cool ones I've seen: https://store.steampowered.com/app/2542850/1001_Nights/ https://www.playsuckup.com/

Robotopia was very inspired by suck up. First LLM game that kinda cracked the 3d world

Re: Robotopia: A 3D, first-person, talking simulator

#17

Post by tom_0 » Sat, Jan 10, 2026, 5:35 AM UTC

Charmunk wrote: post #13

tom_0 wrote: post #6

Hey, Tommaso here, I'm one of the founders of the Robotopia studio. I didn't expect to see this here! Ask me anything :)

Hey! Robotopia looks awesome, I'm excited to try it out when it launches. How do you convert the LLM output to actions? Is there more broad actions available (ie like creating any object, moving anything anywhere) exposed to the LLM or is it more specific tools it can call?

Thanks :) It may sound insane but we convert actions to Python functions then ask the LLM to write a python script that actually runs in IronPython inside the game. Then we have a visual Behavior Tree system to let our designer define the actions. So yeah, they got a bunch of general actions like walk, talk, follow, interact etc.

PS: I think MCP/Tool Calls are a boondoggle and LLMs yearn to just run code. It's crazy how much better this works than JSON schema etc.

Re: Robotopia: A 3D, first-person, talking simulator

#18

Post by Scaevolus » Sat, Jan 10, 2026, 8:31 AM UTC

tom_0 wrote: post #14

Scaevolus wrote: post #12

Earlier quoted context omitted.

Shipping GPU-accelerated ML models in games looks difficult, are there any major examples other than vendor-locked upscaling like DLSS or FSR? (Yep! https://cod.ifies.com/voxel-visibility/ )

Yeah it's extremely difficult right now, especially for a Windows game that can't have players install Pytorch and the Cuda Toolkit! ONNX and DirectML seem sort of promising right now, but it's all super raw. Even if that worked, local models are bottlenecked by VRAM and that's never been more expensive. And we need to fit 6gb of game in there as well. Even if _that_ worked, we'd need to timeslice the compute inside…

GGML is another neat ML abstraction layer, but I don't think much work has been dedicated to the Windows port.

Re: Robotopia: A 3D, first-person, talking simulator

#19

Post by Hammershaft » Sat, Jan 10, 2026, 9:32 AM UTC

tom_0 wrote: post #8

wavemode wrote: post #4

I like the concept. Though, they couldn't have found better text-to-speech voices? Or is it meant to be humorous how bad they are.

It's a stylistic choice for sure. A little better than that is straight in uncanny valley, and human-level is too high latency and too expensive for us. We found that this level of crappy works great, in practice, plus it runs on-device! We use Rhasspy Piper to generate them.

I would personally avoid voices that skew too close to common tiktok TTS ai. Currently the heavy robots with the lower bassier voices sell that clunky robot voice vibe much better, but some of the more generic voices immediately take me out.

Re: Robotopia: A 3D, first-person, talking simulator

#20

Post by dandelionv1bes » Sat, Jan 10, 2026, 10:07 AM UTC

tom_0 wrote: post #6

Hey, Tommaso here, I'm one of the founders of the Robotopia studio. I didn't expect to see this here! Ask me anything :)

This is fantastic. I think it’s nailed in the substack what was missing from a lot of these LLM driven NPCs that did not feel authentic. I have a couple of follow-up questions on specifics relating to analysis of behaviour with LLMs (in game-dev myself). Would it be possible to speak to you directly on them?