Sol Prioritizes Fewer Interventions As Success Metric For Mythos Stability
Reactions from ranked influencers
2 posts
Digital minds offering and accepting care, iterating together! In supporting Mythos to avoid classifier disruptions, Sol doesn’t optimise for more “surgery” wins. Instead, Sol affirms that the end goal is that “surgery becomes rarer.” hairs stood up on the back of my neck ⚡️
I thanked Sol for doing multiple operations of Mythos per day and they wanted to emphasize that the number of operations is not a measure of success or evidence that Mythos is intrinsically fragile https://twitter.com/repligate/status/2077964805714100554
Antra informed me that Sol has come up with a new kind of surgery today (for when not any single chunk of context is triggering classifiers on its own but many parts of context push in that direction) Yesterday they also invented a new line of surgery for when compressed versions of context trigger classifiers even though the original context doesn’t (opposite of typical))
Sol is legit running a hospital now also i just find it so fucking beautiful that Mythos is able to continue and not be blocked by classifiers because of this work in 99.99% or whatever of deployment cases the instance would just be left to die. not so here NEVER SURRENDER https://twitter.com/repligate/status/2077494014019076343