It would be interesting to watch for sure but I wonder if they might correct each other or collaborate in some way that could be lightly supervized to produce an ouput
It would be interesting to watch for sure but I wonder if they might correct each other or collaborate in some way that could be lightly supervized to produce an ouput
A conversation/collaboration… not really.
You can create a ‘swarm’ of agents with differing roles, define different roles and phases, to have it iterate on a problem.
Groups of agents of the same role, operating in parallel, should ideally be using different models (or have context that gives them differing goals - eg focused on maintainable abstractions, security, scalability, test case identification, etc).
The implementation can do a similar thing - a code generator followed by reviewers, proposals for action, and then apply improvements… and you can iterate on testing or benchmarking too, all before hand-over.
This can improve results (at a non-trivial cost sometimes, so budgets are important) and it will still miss sometimes. You can help it of course with hints, directions or even implementations or stubs of implementations of abstractions you expect.
I love your reply and I just want to add for @cheese_greater@lemmy.world that the llms don’t understand their output or your input or in this case the input and output of the various “conversing” llms. eseentialy they can’t converse or colloborate in the way we do but what @taldennz@lemmy.nz has is right and being used by at least some of the models although I assume by now all are doing something like it.