AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is There a Way to Solve the Problem of the Sowar?
In his experience with large language models, which has predominantly been through gpt three, the issue that i feel like is the hardest nut to crack. There is what some called the tendency of the model to hallucinate. And and the sowar just doesn't seem to be able to say, i don't know the answer to that - it will just be riff if it doesn't have something to build on.