[LASR]

The problem with agents is divergence. Very quickly, an ensemble of agents will start doing their own things and it’s impossible to get something that consistently gets to your desired state.

There are a whole class of problems that do not require low-latency. But not having consistency makes them pretty useless.

Frameworks don’t solve that. You’ll probably need some sort of ground-truth injection at every sub-agent level. Ie: you just need data.

Totally agree with you. Unreliability is the thing that needs solving first.

[debo_]

> The problem with agents is divergence. Very quickly, an ensemble of agents will start doing their own things and it’s impossible to get something that consistently gets to your desired state.

Sounds like management to me.

[mycall]

Sticky goals and reevaluation of tasks is one way to keep the end result on track.

How does gpt o1 solve this?