John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges

Sure, here you go: link to this video Summarizing: 1. Obviously you can't completely "solve" truthfulness because people disagree on what is and is not true. But you can go a long way. 2. The models do know what they don't know. Their level of uncertainty is not only expressed in the final token logprobs but also seems to be reified somehow, such that they can express their own level of certainty in words. 3. Many of the problems are introduced by subtle issues introduced during training which effectively teach the AI to guess. One example is by training on QA data sets where the answer is never "I don't know". RLHF introduces its own problems because the human trainers don't know what the model knows,…

There is this idea that the goal of RLHF is to make ChatGPT woke or as you put it to lobotomize it. I suspect that this is a conspiracy theory. There's a very good talk by John Schulman, chief architect of ChatGPT 0, where he explains that if you don't include a RL component in your training, you're essentially doing imitation learning. It's well known that imitation learning fails miserably when presented with conditions that are not in your training set, i.e., answering questions that don't exist on the Internet already. So the goal of RLHF is actually to reduce hallucination. 0 link to this video

…upervised learning scenario where we ask the model to use its internal knowledge to answer a question and compare its answer to one written by a human. If the two answers essentially say the same thing, but in different words, in the supervised learning case the model is penalized. In the RL case, it’s rewarded. That’s the difference. 1. link 2. link to this video…

This is exactly the reason OpenAI isn't afraid of the open-source community, like many kneejerk opponents of regulatory capture assume (they are probably still afraid of Google). Also why they still do the expensive and cumbersome RLHF training, instead of those deceptively cheap and fast finetunes. They understand their own tech and why there isn't free lunch. Recently, John Schulman explained the issue with behavior cloning and it's a very typical ML problem.1 Basically: what are we training the model to do? The model updates after finetuning in a holistic manner, based on the sum total of its content and capability. Suppose GPT-4 can correctly answer to many requests because it knows co…

…have information about their uncertainty but that it remains an open problem as to how to express that uncertainty in natural language. One of the big issues with trying to prevent the model from hallucinating is that you can err too much on the side of caution, causing the model to lie about things it actually does know the correct answer to. 1 link to this video…