[lmeyerov]

Agreed.

Agent reasoning systems should learn based on past and future use, and both end users and maintainers should have power in how they work. So projects naturally progress on adding guard rails, heuristics, policies, customization, etc. Likewise, they first do it with simple hardcoding and then swapping in learning.

As we have built out Louie.ai with these kinds of things, I've appreciated ChatGPT as its own innovation separate from the underlying LLM. There is a lot going on behind the scenes. They do it in a very consumer/prosumer setting where they hide almost everything. Technical and business users need more in our experience, and even that is a coarse brush...