Hard AI

The recent release of live voice from ChatGPT-4o and a similar product Google gave me an idea. Instead of having an agentic AI that takes a long time to complete a task, we have an AI agent, that controls other agent tasks. Lets call it an AI bridge. So the bridge can always respond immedieatly, and have an overview of everything it controls in its context window. It can also be run without user input, so it can give a status to the user.  And example could be to find the address from a list of companies. The AI bridge would then create a task for that, and the task would make some program that could use an API or search to get that information. The bridge would then give a progress to the user, how the programming and retrieval is going. The user can then get the bridge to do multiple tasks at the same time.

The missing piece for AGI AGI is getting closer, but there are still one piece missing. The big context window seems to be solved. Especially the Mamba architecture seems to be very promising. According to wikipedia it has an inferience speed of O(1) and training speed of O(n), whatever that means. But the big hurdle is still hallucination and wrong logical reasoning.  If we can get that fixed, so we can always trust that anything that is in the context window is included in the reasoning, we will have achieved AGI.   The easy way to do this is the ability for an LLM to return "I don't know". It can be done by training the LLM normally, but with additional training data in a question/answer form (that an agentic AI will be using for AGI).  After training the LLM is tested against the Q/A, and is the retrained with all the answers it got wrong. An AI is used to validate the result - and since it knows the anwers from the training set, it has a high accuracy of figuring out...