Transformers do not maintain hidden state between tokens. In this sense they cannot have an inner monologue.
If you force one to output only a single token, it is constrained to doing a single pass of each layer on the problem. If you encourage it to show its working, you are literally giving it more compute to throw at the problem as well as a scratchpad (its output) for a working memory.
These psychological-style experiments and the conclusions they draw are… I don’t know. Exhausting.
If you force one to output only a single token, it is constrained to doing a single pass of each layer on the problem. If you encourage it to show its working, you are literally giving it more compute to throw at the problem as well as a scratchpad (its output) for a working memory.
These psychological-style experiments and the conclusions they draw are… I don’t know. Exhausting.