top | item 46545636

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

104 points| psawaya | 1 month ago |elbowgreasegames.substack.com

51 comments

order

tom_0|1 month ago

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

Tossrock|1 month ago

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.

dandelionv1bes|1 month ago

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?

AlphaWeaver|1 month ago

Do you think there's a path where you can pregenerate popular paths of dialogue to avoid LLM inference costs for every player? And possibly pair it with a lightweight local LLM to slightly adapt the responses? While still shelling out to a larger model when users go "off the rails"?

Charmunk|1 month ago

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?

d3rockk|1 month ago

This has insanely incredible potential for language learning. Do you plan to implement support for additional languages?

Scaevolus|1 month ago

Are the LLMs run on-device, or does this use cloud compute?

(Off-topic AMA question: Did you see my voxel grid visibility post?)

malchow|1 month ago

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.

Workaccount2|1 month ago

I strongly suspect that the advent of LLMs stalled the new elder scrolls game another 5-6 years.

4b11b4|1 month ago

I'm imagining a version of this where you have to use various prompt- or data-centric attacks to navigate scenarios

tom_0|1 month ago

We want to gamify prompt hacking and give people an UI to add/remove chunks of the system prompt. It'll be unlocked by collecting widgets around the place.

Rooster61|1 month ago

This looks like a lot of fun. Is there a way to use text rather than speech for input? I'm not particularly fond of my voice getting sent to an LLM.

tom_0|1 month ago

Yeah, there's a toggle to type you can switch at any time, it actually lowers latency.

wavemode|1 month ago

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.

tom_0|1 month ago

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.

johnea|1 month ago

Max Headroom?

gimun|1 month ago

Nice concept and good try!

tom_0|1 month ago

Thanks :)