[HN Gopher] Robotopia: A 3D, first-person, talking simulator
       ___________________________________________________________________
        
       Robotopia: A 3D, first-person, talking simulator
        
       Author : psawaya
       Score  : 100 points
       Date   : 2026-01-08 19:55 UTC (5 days ago)
        
 (HTM) web link (elbowgreasegames.substack.com)
 (TXT) w3m dump (elbowgreasegames.substack.com)
        
       | 4b11b4 wrote:
       | I'm imagining a version of this where you have to use various
       | prompt- or data-centric attacks to navigate scenarios
        
         | tom_0 wrote:
         | 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.
        
       | fosterfriends wrote:
       | I'm so excited to see LLMs used more creatively in video games.
       | So many new mechanics can be unlocked with LLMs as judges
        
         | psawaya wrote:
         | Agreed!
         | 
         | Some other cool ones I've seen:
         | https://store.steampowered.com/app/2542850/1001_Nights/
         | https://www.playsuckup.com/
        
           | shminkle wrote:
           | Robotopia was very inspired by suck up. First LLM game that
           | kinda cracked the 3d world
        
       | wavemode wrote:
       | 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 wrote:
         | 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.
        
           | Hammershaft wrote:
           | 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.
        
             | tom_0 wrote:
             | 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.
        
       | lifetimerubyist wrote:
       | 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...
        
         | shminkle wrote:
         | I had no idea this game had LLM NPCs. Interesting
        
       | tom_0 wrote:
       | Hey, Tommaso here, I'm one of the founders of the Robotopia
       | studio. I didn't expect to see this here! Ask me anything :)
        
         | Scaevolus wrote:
         | Are the LLMs run on-device, or does this use cloud compute?
         | 
         | (Off-topic AMA question: Did you see my voxel grid visibility
         | post?)
        
           | tom_0 wrote:
           | 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)
        
             | Scaevolus wrote:
             | 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/ )
        
               | tom_0 wrote:
               | 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 360deg 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!
        
               | Scaevolus wrote:
               | GGML is another neat ML abstraction layer, but I don't
               | think much work has been dedicated to the Windows port.
        
               | tom_0 wrote:
               | 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.
        
               | lostmsu wrote:
               | You don't have to install the whole CUDA. They have a
               | redistributable.
        
               | tom_0 wrote:
               | Oh, I can't believe I missed that! That makes whisper.cpp
               | and llama.cpp valid options if the user has Nvidia,
               | thanks.
        
               | lostmsu wrote:
               | Whisper.cpp and llama.cpp also work with Vulkan.
        
               | tom_0 wrote:
               | Yeah, I researched this and I absolutely missed this
               | whole part. To my defense I looked into this in 2023
               | which is ages ago :) Looks like local models are getting
               | much more mature.
        
         | Charmunk wrote:
         | 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?
        
           | tom_0 wrote:
           | 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.
        
             | woodrowbarlow wrote:
             | uhhh... you're running generated code on your customers'
             | PCs? what kind of sandboxing do you have?
        
               | tom_0 wrote:
               | Fair reaction tbh. Right now there's a time watchdog +
               | I'm entirely disabling all I/O and import, But going
               | forward I want to replace it with a proper sandboxing
               | tech... things I looked into are V8 isolates, compilation
               | to WASM, implementing our own gutted python interpreter,
               | spinning up a locked down process, and others. I'm
               | definitely aware of the risk here. The good news is that
               | unless we get pwned, LLMs are very unlikely to write
               | malicious code for the user.
        
         | dandelionv1bes wrote:
         | 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?
        
           | tom_0 wrote:
           | Thanks :) If you want I'm on the discord linked on our
           | landing page, it's fun stuff to talk about!
        
             | dandelionv1bes wrote:
             | Amazing! Thanks will join.
        
         | Tossrock wrote:
         | 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.
        
           | tom_0 wrote:
           | 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.
        
         | d3rockk wrote:
         | This has insanely incredible potential for language learning.
         | Do you plan to implement support for additional languages?
        
           | tom_0 wrote:
           | Yes, but every language is going to be a "port", not
           | something contracted out like traditional localization. I
           | haven't decided how exactly but language conversion will land
           | somewhere between these two extremes: 1. (expensive) pick a
           | suite of "native" models (eg. models from China), TTS, ASR.
           | Rewrite all the prompts in the target language. Revalidate
           | all characters by hand 2. (cheap) slap a translation model
           | around input and output and let the game run in English
           | internally. My gut feeling is that this could have very poor
           | results though and increase latency.
           | 
           | It's definitely a research project, this has never been done
           | before.
        
         | AlphaWeaver wrote:
         | 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"?
        
           | themanmaran wrote:
           | Not the founder, but having run conversational agents at
           | decent scale, I don't think the cost actually matters much
           | early on.
           | 
           | It's almost always better to pay more for the smarter model,
           | than to potentially give a worse player experience.
           | 
           | If they had 1M+ players there would certainly be room to
           | optimize, but starting out you'd certainly spend more trying
           | engineer the model switcher than you would save in token
           | costs.
        
             | tom_0 wrote:
             | I agree, trying to save on costs early on is basically
             | betting against things getting better. Not only that but in
             | almost every case people prefer the best model they can
             | get!
             | 
             | Not only that but I think our selling point is rewarding
             | creativity with emergent behavior. I think baked dialogue
             | would turn into traditional game with worse writing pretty
             | quick and then you got a problem. For example, this AI game
             | here does multiple choices with a local model and people
             | seem a bit mild about it.
             | 
             | We could use it to cache popular QA, but in my experience
             | humans are insane and nobody ever says even remotely
             | similar things to robots :)
             | 
             | [1] https://store.steampowered.com/app/2828650/The_Oversigh
             | t_Bur...
        
       | johnea wrote:
       | Max Headroom?
        
       | malchow wrote:
       | 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 wrote:
         | I strongly suspect that the advent of LLMs stalled the new
         | elder scrolls game another 5-6 years.
        
           | malchow wrote:
           | What's interesting is you might not want to see de novo AI-
           | generated storytelling (slop factor), but you might really
           | like the way AI can make a story crafted by humans more
           | interactive.
        
             | mavamaarten wrote:
             | It's going to be a balance act. There's going to be plenty
             | of companies that are just going to be greedy and will
             | generate AI slop without checking, which will undoubtedly
             | tank the quality of many games in the near future.
             | 
             | When applied smartly and with human supervision, I think
             | that AI could easily help humans build game worlds and
             | stories that were previously impossible to achieve.
        
           | tom_0 wrote:
           | Hah from my knowledge of traditional AAA, there is 0 chance
           | any AAA in development right now uses LLMs. A lot of them
           | don't even use it for coding and gamedevs' mood about AI is
           | abysmal.
        
             | Workaccount2 wrote:
             | Let me just remind you that Microsoft owns the elder
             | scrolls franchise now, for better or worse.
        
               | tom_0 wrote:
               | I know, but it's a bit of an unstoppable force vs
               | immovable object situation unless something changed. If
               | they do it, I hope it'll be better than Copilot
               | integrations :)
        
           | dyauspitr wrote:
           | Why? Because they feel like it needs to be a part of the
           | game?
        
       | gimun wrote:
       | Nice concept and good try!
        
         | tom_0 wrote:
         | Thanks :)
        
       | Rooster61 wrote:
       | 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 wrote:
         | Yeah, there's a toggle to type you can switch at any time, it
         | actually lowers latency.
        
       ___________________________________________________________________
       (page generated 2026-01-13 23:01 UTC)