Play uncanny experience
The Uncanny Valley's itch.io pageResults
| Criteria | Rank | Score* | Raw Score |
| Creativity | #2863 | 3.120 | 3.462 |
| Enjoyment | #3567 | 2.496 | 2.769 |
| Overall | #3635 | 2.681 | 2.974 |
| Presentation | #4236 | 2.427 | 2.692 |
Ranked from 13 ratings. Score is adjusted from raw score by the median number of ratings per game in the jam.
How does your game fit the theme?
It reverses the interaction role humans and AI has, where the player is the one who has to assist and give answers to the AI (robot)
Did your team create the vast majority of the art during the 48 hours?
Yes
We created the vast majority of the art during the game jam
Did your team create the vast majority of the music during the 48 hours?
Yes
We created the vast majority of the music during the game jam
Leave a comment
Log in with itch.io to leave a comment.
Comments
Obviously your AI is limited, but it's just good enough to maintain the illusion that I'm actually talking to a cohesive character. Reminds me of ELIZA or other really early chatbots.
Really fun concept. It's like how it feels to be the AI getting asked the questions! It would be cool if somebody made this with something like the ChatGPT api.
I actually really liked talking to a robot about cats, that was fun.
I am glad you did :)
Did you find out about the problems the robots are having with cats on Mars?
Definitely uncanny! The typing sounds and the robot really create a creepy atmosphere. Although I didn't quite understand what I was doing... still, good job!
Thanks, I didn't know either what exactly I was doing and the result. And is not extensively tested. I really wonder how is the experience for others :D, since depends on how each writes and what.
Do the prompts you get relate to what you write? If yes, how does it work?
Do you really want me to break the magic? :)
Yes, it relates to what you write.
The simulation works as follows:
There are a series of pools of sentences and questions (12) sorted by topic or "mood".
There is a mood selector and a set and sorting of those pools is created (4 of them)
There is a mood score, that varies based on your previous answer (if it found a match to your answer in the pool or not).
For each answer, it goes through the current text pools available in the mood selector and gives them a score based on the words given by you, and if there is some coincidence. There is also a "topic" control variable, which gives more weight to the sentences that contain the longest word contained in the previous prompt is displayed, to help simulate continuity.
The answer that scores the highest from those pools gets picked. If the answer is not a question, it picks a random question as a follow-up.
It also can detect certain rude words.
If no sentence from the pool scores, there is a series of fall-back checks triggered to save the situation, and if none is found it comes with the "insufficient cooperation" answer.
Thanks for the thorough explanation, that's awesome! I understand having the generative AI rule for this jam, but I am absolutely positive that large language models in particular will change how we perceive videogames. I am puzzled as to why there is so much resistance, especially in the indie game dev scene, over genertaive AI.