Sandhini Agarwal: We now have a variety of subsequent steps. I undoubtedly suppose how viral ChatGPT has gotten has made a variety of points that we knew existed actually bubble up and change into important—issues we wish to clear up as quickly as attainable. Like, we all know the mannequin remains to be very biased. And sure, ChatGPT is superb at refusing dangerous requests, but it surely’s additionally fairly straightforward to put in writing prompts that make it not refuse what we needed it to refuse.
Liam Fedus: It’s been thrilling to observe the varied and artistic purposes from customers, however we’re all the time targeted on areas to enhance upon. We predict that by an iterative course of the place we deploy, get suggestions, and refine, we are able to produce essentially the most aligned and succesful know-how. As our know-how evolves, new points inevitably emerge.
Sandhini Agarwal: Within the weeks after launch, we checked out among the most horrible examples that folks had discovered, the worst issues folks have been seeing within the wild. We sort of assessed every of them and talked about how we must always repair it.
Jan Leike: Typically it’s one thing that’s gone viral on Twitter, however we’ve got some individuals who truly attain out quietly.
Sandhini Agarwal: Loads of issues that we discovered have been jailbreaks, which is unquestionably an issue we have to repair. However as a result of customers need to attempt these convoluted strategies to get the mannequin to say one thing dangerous, it isn’t like this was one thing that we utterly missed, or one thing that was very shocking for us. Nonetheless, that’s one thing we’re actively engaged on proper now. Once we discover jailbreaks, we add them to our coaching and testing knowledge. The entire knowledge that we’re seeing feeds right into a future mannequin.
Jan Leike: Each time we’ve got a greater mannequin, we wish to put it out and check it. We’re very optimistic that some focused adversarial coaching can enhance the scenario with jailbreaking lots. It’s not clear whether or not these issues will go away fully, however we expect we are able to make a variety of the jailbreaking much more troublesome. Once more, it’s not like we didn’t know that jailbreaking was attainable earlier than the discharge. I believe it’s very troublesome to actually anticipate what the actual security issues are going to be with these methods when you’ve deployed them. So we’re placing a variety of emphasis on monitoring what individuals are utilizing the system for, seeing what occurs, after which reacting to that. This isn’t to say that we shouldn’t proactively mitigate security issues after we do anticipate them. However yeah, it is vitally arduous to foresee every part that can truly occur when a system hits the actual world.
In January, Microsoft revealed Bing Chat, a search chatbot that many assume to be a model of OpenAI’s formally unannounced GPT-4. (OpenAI says: “Bing is powered by one in all our next-generation fashions that Microsoft personalized particularly for search. It incorporates developments from ChatGPT and GPT-3.5.”) The usage of chatbots by tech giants with multibillion-dollar reputations to guard creates new challenges for these tasked with constructing the underlying fashions.
