Yes, systems comprised of chains of calls to an LLM can be much more capable than a few individual, human-invoked completions. The effort needed to build such systems is usually tiny compared to the effort and expense needed to train the underlying foundation models.
Role architectures provides one way of thinking about and aligning such systems.
My post on steering systems also has some potentially relevant ways for thinking about these systems.
Yes, systems comprised of chains of calls to an LLM can be much more capable than a few individual, human-invoked completions. The effort needed to build such systems is usually tiny compared to the effort and expense needed to train the underlying foundation models.
Role architectures provides one way of thinking about and aligning such systems.
My post on steering systems also has some potentially relevant ways for thinking about these systems.