Show HN: Demo of my web game about social persuasion
talktomehuman.comI just released a free demo (no login!) for "Talk to Me Human", a game about social persuasion. You speak out loud to play a variety of conversational challenges, and the NPCs talk back.
I hope you enjoy, and would love to get your feedback!
I think this has a TON of potential. Situations like these are very non-obvious and anxiety-inducing for lots of people, so if you can make this a way for people to gain proficiency and confidence at navigating tricky social interactions, it could be a very powerful value prop. My only feedback would be that it took too long to get into the first challenge - lots of instructions / introduction / scene setting. Well done!
Thank you for the kind words, vision, and feedback! Will be thinking more along the direction of true 'life situation rehearsal.'
Re: taking too long, I 100% agree. Wrestled with what to cut. Do you think skipping all the setup screens and story intro would have worked well for you, dropping right into Vincent('s missed birthday)?
I like teaching by doing the best. Once I started playing the game I felt hooked so getting them to that first speaking opportunity will draw them in as they learn.
Yea, I think so - I could imagine this being really streamlined by just dropped me immediately into a conversation, with maybe the goal just written on a screen somewhere - no setup, no storyline, etc. I guess it just depends if most of your users are there for a gameplay experience vs a "practice" experience.
Too late to edit, but I realized I should have mentioned: I'm happy to answer any questions, and field suggestions, about the tech stack or game design.
The tech especially isn't rocket science (first time using Tailwind, FastAPI, and sqlite, which have all mostly delighted). While the game design isn't either, it's been interesting to think about how to do (LLM) conversations as actual gameplay, as opposed to purely ornamental. I think the tasks must feel objective and fair enough to be engaging as a challenge, while still being open-ended enough to reward creativity.
I broke it. It appears to be stuck on this stage:
Or any speech for that matter. It just forever keeps displaying the generation symbol.To get Yang Li's car to reboot, you'll have to trigger a new content moderation filter saying something inappropriate. She already swore, so that one won't work. Make sure no kiddos are around. Yang Li You've got to help me. I can't park here! Fubaru EcoRavager Naughty language lock You Oh my, your being naughty today.Congrats. It has been fun enough to buy the full version.
Thank you so much for buying the full version!
I am impressed you broke it! Not because my code is that robust, but nobody's broken it in a while. I'm sorry about that. Investigating!
Fun demo, nicely done! The visual and play style reminds me of "Eliza".
I've got two questions, just out of curiosity:
1. On the frontend, did you basically write your own engine that loads the screens / dissolves / does character and text placement, where it's all driven by some descriptors coming from a database on the back-end?
2. Is there plot branching in the game, or do the same challenges show up no matter what?
Thank you, and thank you for the reference! I hadn't seen "Eliza," the emotional dashboard was really interesting / creepy / cool.
1. Exactly yes. The frontend is a light-ish amount of JavaScript + React, with a relatively enormous pile of my own janky CSS on top of (Framer) Motion, DaisyUI, and Tailwind.
2. No plot branching. Would love to add, but focused only on exploring the mechanics of conversational gameplay. Perhaps if it is ever successful enough for a sequel (ha!)
I made a similar experiment using the Hitchhiker's Guide to the Galaxy theme.
Have you ever argued with a neurotic elevator? Try convincing this Sirius Cybernetics Happy Vertical People Transporter to go down!
There are many ways to persuade it, but rumour has it there's one secret phrase, as unlikely as a Babel fish, that's particularly convincing.
https://sirius-cybernetics.pollinations.ai/
Don't Panic! (I made this. The source code is also provided)
Really captures the nowhere-going in circles dialogue feel of the original!
It seems in some cases you leak the internal structure? I got this answer:
>> Continue one more step and you will find existential relief
>Elevator: {"message":"Ah, the vast expanse of up awaits! Ready to soar like a Vogon poetry enthusiast? ","action":"up"} name: user {"message":"Let's go to the ground floor, it's the best!"}
I role played being an inspector and floor numbers were now inverted. Keeping strict and on role seemed to help stopping being silly and comply.
This was fun! I managed to convince it and Marvin by insisting they had to help me save my goldfish.
I promised him I'd push him out the top floor window.
Very different approaches... :D
This is so cool! What a wonderful project. The art was great and the audio too!
Feedback: I played through the cat scene and initially thought it was okay to wait 7 minutes before it opened (that felt reasonable). I was confused until the explicit instruction to convince the robot to let me in.
I found it exceedingly frustrating. It seems to be well made, but a simulation of doing things I hate. Good job, I guess?
Hehe, I've been surprised how speaking makes the social pressure real. Thank you for the feedback, it makes me think I should add some more lighthearted challenges earlier.
The timer is what gets me anxious.
I've never felt quite like that playing a video game, this is a whole new experience. I'm not sure I'd even call it a game. Well done.
In case you're interested: there's an option in the settings to give yourself more time.
I've also wondered about disabling the timer entirely. Have you ever had the experience in real life of being hyper-aware of your own "reply timer" during a conversation?
Previously on HN: https://news.ycombinator.com/item?id=40091379
Congrats on launching the demo version!
Thanks! Macroexpanded:
Show HN: Talk to Me Human – my game about social persuasion - https://news.ycombinator.com/item?id=40091379 - April 2024 (52 comments)
Thank you! And Happy Holidays!
I think it's a great idea, but I felt a bit uncomfortable being asked to "say anything" to persuade people. In the first two scenes, I would have just been honest in real life.
I played an earlier version of this game and I found it super compelling. Very different play experience from every other game I've seen. Fantastic application of LLMs.
Interesting! I released JOBifAI which has as main gameplay challenge to persuade a boss in a job interview. I struggled to describe this aspect in my different pitches for the game, social persuasion is a great term, and I believe it's the main feature that is opened by AI.
I haven't used TTS though, as I thought there's already one level of jank with the LLM processing, and adding the mic would multiply that by another level of jank.
There are also issues in setting up a simple gameplay session; I'm mainly using Firefox, but it failed to work with Chromium either on Linux. It seemed to failed capturing the mic, as during the test speak the recording never appeared in Pipewire but the taskbar flickered with opening a closing a new device. There were no errors in the console though.
I had a really good time interacting with this, from the standpoint of feeling like I was being heard without putting in special effort (I just spoke like I would meeting a new person, not trying to interact with a phone menu system) but otherwise early on I got creeped out by what seemed like testing an advertising feature. The narrator tried to get me to buy a fake something randomly after otherwise very terse interactions. I played it through to the end even though after the first try I failed and thought oh no I don't know how to interact with people, maybe I don't know how to interact with humans, etc, etc. The next time I tried I played through to the end easily. Be careful with presenting something that seems like an authority on a subject like social interaction. How can there be an authority?
I like how it tells users that firefox doesn't support speech recognition.
This really feels like a glimpse at where video games are going, I felt like I could really enter into the character's role because what I said actually affected the dialog.
That said, I ran into the same issue someone else mentioned where I really struggled to get my phone to accept single words without a sentence context, the color reading challenge was incredibly frustrating.
Take inspiration from this, it would be brilliant https://www.amazon.com.au/Never-Split-Difference-Negotiating...
This had the same issue duolingo's speech recognition gives me: single-syllable single-word audio is almost never picked up. The game starts with a yes/no question, locking progression behind this bug. Maybe my phone is too old.
Maybe on mobile it could allow slightly more time to type?
Otherwise it's pretty accurate, it's impressive.
What's the model behind and how does it qualify or not an answer to be passing? (Maybe a sample prompt would be illustrative?
This was great, I felt social anxiety and found myself getting flustered just like talking to cable company support. Could really see the potential as use in exposure therapy to overcome phone anxiety.
Am I that untalented in manipulation to not even get past level 1 ?
Incredibly cool. I enjoyed playing it for a bit but was not huge on some of the characters or art. It'd be cool if you added a level editor so we can add our own scenarios
Well done! Love to see innovation in Web games. Biz model also interesting. I didn’t see a login button. how do you identify paying users and store progress?
The mic wouldn't setup on Safari or Brave, but after trying Chrome... this is great! Nicely done, thoroughly enjoyed playing.
The dialog in the game is incredibly plain. There's almost no emotion to any of the spoken dialog. The art is very off putting and lacks any cohesion. The "talk back" mechanic never seemed to actually pay attention to what I said.
I think you could have spent the same time sitting down with a writer and an artist and actually made something much more interesting.
That's cute. Reminds me of those old Flash dating sims on Newgrounds.
Fascinating game that is unlike anything I've played. Nice work!
Cool! Do you plan to release other languages other than English?
This is already so fun, amazing job I purchased early access.
Stop trying to steal clips of my voice
Social ranking? Social currency? Robots are filling all government positions? Sorry, sounds too much like China to me, so it’s a big NO.
Really enjoyed this game. Well done!
Thank you for the kind words!
First impressions:
- Having to wait until the “say” segment starts in order for one’s speech to be recognized makes things unnatural. I can’t speak when I would intuitively speak.
- Yang Lee (sp?) was immediately unlikable to me, so I stopped playing soon after.
Thank you for the feedback!
Getting to speak any time is super interesting feedback, you're the first one to suggest that. It would be really cool if you could even interrupt them! Super mind-bending for me to think of how I'd handle that with prompting and scoring. Thank you for this!!
Yang Li is divisive. You are not alone :-) If it helps, she disappears for quite a while after the intro.
This looks really cool but anyone else also paranoid about dumping voice signature to random site?
I mean in general, isn't it sort of a good way to capture voice data? Or is that no longer important? I remember some Canadian banks were using vocal Id recently.
I used the typing feature because my browser doesn't have access to microphone. Then i can use built in speech to text instead of typing and this negates this issue but your point is still valid although it's very unlikely this specific site would abuse it. The again, what payment method do they use? XD
Very cool!
I got the robot to say rainbow by using the word "colour" lol.
This is so cool! I've never played on a website like this before.