Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

elbowgreasegames.substack.com

Post reply on HN
Print view View original

21–30 of 54 posts

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

#21

Post by tom_0 »

Hammershaft wrote: post #19
tom_0 wrote: post #8

Earlier quoted context omitted.

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.

Unfortunately, they are close because some of them ARE tiktok AI voices you heard! I'm working on hiring VAs to make custom datasets, though. We'll have our own unique voices by 1.0 for sure.

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

#22

Post by tom_0 »

Scaevolus wrote: post #18
tom_0 wrote: post #14

Earlier quoted context omitted.

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.

GGML still runs on llama.cpp, and that still requires CUDA to be installed, unfortunately. I saw a PR for DirectML, but I'm not really holding my breath.

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

#23

Post by tom_0 »

dandelionv1bes wrote: post #20
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?

Thanks :) If you want I'm on the discord linked on our landing page, it's fun stuff to talk about!

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

#24

Post by dandelionv1bes »

tom_0 wrote: post #23
dandelionv1bes wrote: post #20

Earlier quoted context omitted.

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?

Thanks :) If you want I'm on the discord linked on our landing page, it's fun stuff to talk about!

Amazing! Thanks will join.

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

#25

Post by Tossrock »

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 :)

Do you have a budget per-player of cloud usage? What happens if people really like the game and play it so much it starts getting expensive to keep running? I guess at $0.79 / Mtok llama70B is pretty affordable, but a per-player opex seems hard to handle without a subscription model.

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

#28

Post by tom_0 »

Tossrock wrote: post #25
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 :)

Do you have a budget per-player of cloud usage? What happens if people really like the game and play it so much it starts getting expensive to keep running? I guess at $0.79 / Mtok llama70B is pretty affordable, but a per-player opex seems hard to handle without a subscription model.

Our initial plan was to simply ask enough for the game that the price would cover the costs on average... but that means that we're basically encouraged to have people play the game as little as possible? We're looking into some kind of subscription now, it sounds weird but I do think it's a better incentive in this case. Plus we can actually ask for less upfront.

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

#29

Post by lostmsu »

tom_0 wrote: post #22
Scaevolus wrote: post #18

Earlier quoted context omitted.

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

GGML still runs on llama.cpp, and that still requires CUDA to be installed, unfortunately. I saw a PR for DirectML, but I'm not really holding my breath.

You don't have to install the whole CUDA. They have a redistributable.

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

#30

Post by malchow »

This is an incredible foretaste of what AI can enable in gaming. Not replacing humans (the creators here are former leaders from Minecraft), but rather simply unlocking more fun gameplay by offering creativity, humor, and branched storytelling customized to the player.
Post reply on HN