behavior-trees-for-llm-chatbots
king-algorithm-manifesto
behavior-trees-for-llm-chatbots | king-algorithm-manifesto | |
---|---|---|
1 | 2 | |
25 | 7 | |
- | - | |
3.7 | 4.6 | |
about 1 year ago | 27 days ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
behavior-trees-for-llm-chatbots
-
Ask HN: Have advancements in AI given you ideas for new side projects?
I have started several:
- A small example of how to use behavior trees in structuring LLM chatbot applications: https://github.com/keskival/behavior-trees-for-llm-chatbots
- A project for extracting meta-learned reinforcement learning algorithms out of a large language model: https://github.com/keskival/king-algorithm-manifesto
- A proof-of-concept of embodying an LLM chatbot into a Gym PoleCart environment: https://github.com/keskival/embodied-emulated-personas
king-algorithm-manifesto
-
Ask HN: Have advancements in AI given you ideas for new side projects?
I have started several:
- A small example of how to use behavior trees in structuring LLM chatbot applications: https://github.com/keskival/behavior-trees-for-llm-chatbots
- A project for extracting meta-learned reinforcement learning algorithms out of a large language model: https://github.com/keskival/king-algorithm-manifesto
- A proof-of-concept of embodying an LLM chatbot into a Gym PoleCart environment: https://github.com/keskival/embodied-emulated-personas
-
“Just a statistical text predictor”
Looking at Transformer model architecture and their training schemes to understand how they think misses the point. You wouldn't gain insight into how Doom game works by just looking at schematics of an x86 processor.
These systems are Turing complete and they can execute any computation. To see what they actually execute requires looking at what happens in memory while Doom runs, in the activations when the Transformer model executes.
At this time we don't have good tools to extract the actual algorithms and submodels these LLMs execute, but there are reasons to believe there are better algorithms learned in there for example for reinforcement learning than what we have ever been able to engineer.
See for example my research: https://github.com/keskival/king-algorithm-manifesto#readme
What are some alternatives?
embodied-emulated-personas - A project space for Embodied Emulated Personas - Embodied neural networks trained by LLM chatbot teachers