The system one model idea is quite powerful, but it requires decomposing problems into very granular steps and questions.
This is a lot more work than basic zero or few shot prompting of a large general LLM. It's also a bit contrary to the challenge of an autonomous agent in an open ended environment.
It will take time for people to do that kind of work and apply these models in their domais. Similarly it will take time for someone to figure out how to potentially automate the decomposition process so they could be leveraged in more autonomous agents.
The system one model idea is quite powerful, but it requires decomposing problems into very granular steps and questions.
This is a lot more work than basic zero or few shot prompting of a large general LLM. It's also a bit contrary to the challenge of an autonomous agent in an open ended environment.
It will take time for people to do that kind of work and apply these models in their domais. Similarly it will take time for someone to figure out how to potentially automate the decomposition process so they could be leveraged in more autonomous agents.