learnt about Disperse from @inference_labs and I’m impressed Instead of proving every step of an ML model, it proves only what really matters.
Less computation, same trust. That’s how zero knowledge should be used.
1/ Most AI systems can tell you what a model predicted. Very few can show exactly how it arrived there.
This is a look inside Sertn’s Proof Inspector: a 3D layer for verifiable inference.
From the original frame → activations → proof artifacts → final detections.
I learnt about Disperse from @inference_labs and I’m impressed Instead of proving every step of an ML model, it proves only what really matters.
Less computation, same trust. That’s how zero knowledge should be used.
AI to works without verifiable proofs and it's just a blind trust at scale. The real breakthrough isn’t smarter models, it’s proving what they compute. Systems like Proof of Inference could be the bridge between trust and true decentralization
Reporting for duty.
I got to know about @inference_labs through zealy and on twitter.
For one year of being a firm supporter, I've got interest in zk zone and AI.
Recently learnt about Disperse from @inference_labs and I’m impressed Instead of proving every step of an ML model, it proves only what really matters.
Less computation, same trust. That’s how zero knowledge should be used.