Thytu

I simply tested it, result are quite different tbh. Now the big question is "Why".

My first thought would be that it's kinda we, humans, behave. It feels a bit the equivalent of the mom-test. If you ask someone "do you like this", he/she is bias to to say "yes", same goes for LLMs (I took a dummy example but you got the idea).

Anyway, I can be wrong, I can be right, ATM no one knows not even me

The goal isn't entertainment but practical simulation. I'm building tools to automate A/B testing, model marketing campaign responses, and optimize content - all by simulating human behavior at scale. Where behavior trees fall short, language models can capture nuanced user reactions that can't be reduced to simple metrics.

(if I can make it realistic enough lol)

By default the "agent" is pretty limited in actions (only talking / and thinking).

Currently it's up to the user to add its own actions, you can find an example where I gave the agents access to ChatGPT (cf link)

Obviously, some default actions will be added in the future :D

link to example: https://github.com/Thytu/Agentarium/blob/main/examples/3_add...

Thanks for the interest! I use aisuite (cf link) to manage what LLMs to use. You should be able to switch from one provider to an other quite easily (even hugging-face if you want). I don't know if aisuite supports local LLMs tho, might be a good thing to check.

aisuite : https://github.com/andrewyng/aisuite

I just published a brief blog post about IPUs based on my recent meeting with the members of the Graphcore team. I would greatly appreciate your valuable feedback on it! Please feel free to share your thoughts and insights. Thank you!