Comment by HarHarVeryFunny

1 year ago

The "failing" here isn't the short term functional gains, but rather the choice of architectural direction. Trying to add reasoning as an ad-hoc wrapper around the base model, based on some fixed reasoning heuristics (built in biases) is really a dead-end approach. It would be better to invest in a more powerful architecture capable of learning at runtime to reason for itself.

Bespoke hand-crafted models/agents can never compete with ones that can just be scaled and learn for themselves.