What if the machine has a benchmark/training suite for performance. On the benchmark is a task for designing a better machine architecture.
Machine proposes a better architecture. New architecture maybe a brand new set of files defining the networks, topology, and training procedure, or they may reuse networks for components.
For example you might imagine an architecture that uses gpt-3.5 and −4 as subsystems but the “executive control” is from a new network defined by the architecture.
Given a very large compute budget (many billions), the company hosting the RSI runs would run many of these proposals, then the machines that did the best on the bench that are distinct from each other (so a heuristic of distinctness, performance) remain “alive” to design the next generation.
So it is recursive, improvement, and the “selves” doing it are getting more capable over time but it’s not a single AGI improving itself but instead a population. Humans are also still involved and tweaking things (and maintaining the enormous farms of equipment)
What if the machine has a benchmark/training suite for performance. On the benchmark is a task for designing a better machine architecture.
Machine proposes a better architecture. New architecture maybe a brand new set of files defining the networks, topology, and training procedure, or they may reuse networks for components.
For example you might imagine an architecture that uses gpt-3.5 and −4 as subsystems but the “executive control” is from a new network defined by the architecture.
Given a very large compute budget (many billions), the company hosting the RSI runs would run many of these proposals, then the machines that did the best on the bench that are distinct from each other (so a heuristic of distinctness, performance) remain “alive” to design the next generation.
So it is recursive, improvement, and the “selves” doing it are getting more capable over time but it’s not a single AGI improving itself but instead a population. Humans are also still involved and tweaking things (and maintaining the enormous farms of equipment)
Training runs already take months.
I’d expect that to take several generations of models, so double digit numbers of months in an aggressive scenario?
(Barring drastic jumps in compute that cut months long training runs to hours/days).
Read paragraph 2
But yes foom wasn’t going to happen. It takes time for ai to be improved, turns out reality gets a vote.