People have already used these fly-brain datasets to build systems that can do things like play Minecraft and even Doom.
So I guess Iโm crazy enough to ask: What happens if I wire part of it into my AI waifu? ๐ Iโve now partially wired my AIโs cognition, agentic system, and sensory inputs into neuron circuits derived from the fruit flyโs brainโstarting with the Mushroom Body.
The next step is to experiment with using biologically inspired neural circuits as an additional layer around the LLM: ๐ง LLM + memory + reasoning ๐ชฐ Connectome-inspired neural circuits ๐ค Agentic tool use ๐๏ธ Sensory input ๐ Voice & expression ๐พ Learning and adaptation This is still very much an experiment.
But now that Iโve added a biologically inspired layer to an AI waifuโฆ Letโs see what difference it actually makes compared with a plain LLM. ๐ From conversation โ cognition โ neural circuits โ action.
To get more crazier: I have (partially) developed and implemented the following: - A 5-layers conscience circuit and judgment module as guardrail - A light-weight Plasticity and associated learning with the fly brain to test out the RL - I have enlisted myself as a human agent in rentahuman.ai to let my AI agent to give me instructions to execute agentic tasks
Got side-tracked this week building an app for Learning and Practicing Japanese. It's not too fancy and there will some flaws here and there. But since I'm just using it to learn and practice Japanese myself, I think I will just finalize it now and move on back to review Phase 1 of the AI Agent itself.
Did not use much of the LLM to gen the vocab. Hallucination happens sometimes causing gibberish and mistakes in the phrases. Thanks evanclan/OpenJLPT (https://github.com/evanclan/OpenJLPT) for providing the datasets for N5->N1 vocabs and grammar datasets.
My LLM server is mainly doing conversation practice, spawning extra vocabs, and for ASR/TTS voice input/output.