alt Hacker News> These models are trained to be truthful
A more accurate statement would be that these models are trained to fit the training data as closely as possible, regardless of whether the training data reflects the truth.
Replies
slibhb • last Monday at 5:29 PM
No, they're very clearly trained to be truthful.
Well, yes, but remember there is the reinforcement learning that is applied after, and the system prompts that will bend the results.