1 points | by digitalwingman a day ago ago
1 comments
I've been working on scaling my LLM system to production but I'm struggling to meet all of the privacy, security, safety, and ethics standards.
I found this "corrective layer" called Pegasi online. It was founded by some researchers at Carnegie Mellon/ Oxford and Boston Consulting Group.
After running it through some tests, it blew all the benchmarks out of the water.
Just curious if anyone else has heard of them? I really like their nuero-symbolic AI approach.
I've been working on scaling my LLM system to production but I'm struggling to meet all of the privacy, security, safety, and ethics standards.
I found this "corrective layer" called Pegasi online. It was founded by some researchers at Carnegie Mellon/ Oxford and Boston Consulting Group.
After running it through some tests, it blew all the benchmarks out of the water.
Just curious if anyone else has heard of them? I really like their nuero-symbolic AI approach.