← Back to context Comment by busssard 15 days ago it makes sense that that would happen given their training process 2 comments busssard Reply PaulStatezny 14 days ago Could you elaborate? What is it about their training process that would make reasoning loops more likely? busssard 10 days ago its semi automated, and is mostly based on a variety of benchmarks. this is something someone has to spot and design filters for, or let be designed.otherwise the infinite loops that happen get drowned in the statistical noise, of the good runs scoring good results.
PaulStatezny 14 days ago Could you elaborate? What is it about their training process that would make reasoning loops more likely? busssard 10 days ago its semi automated, and is mostly based on a variety of benchmarks. this is something someone has to spot and design filters for, or let be designed.otherwise the infinite loops that happen get drowned in the statistical noise, of the good runs scoring good results.
busssard 10 days ago its semi automated, and is mostly based on a variety of benchmarks. this is something someone has to spot and design filters for, or let be designed.otherwise the infinite loops that happen get drowned in the statistical noise, of the good runs scoring good results.
Could you elaborate? What is it about their training process that would make reasoning loops more likely?
its semi automated, and is mostly based on a variety of benchmarks. this is something someone has to spot and design filters for, or let be designed.
otherwise the infinite loops that happen get drowned in the statistical noise, of the good runs scoring good results.