The purpose of the prompt injection is to influence the output of the model. It does not imply anything about ChatGPT’s capabilities. Most likely it is meant to dissuade the model from hallucinating search results or to cause it to issue a disclaimer about not being able to browse the internet, which it frequently does.
I think it is meant to let them train one model that both can and can’t browse the web in different modes, and then let them hint the model’s current capabilities to it so it acts with the necessary self-awareness.
If they just wanted it to always say it can’t browse the web, they could train that in. I think instead they train it in conditioned on the flag in the prompt, so they can turn it off when they actually do provide browsing internally.
My interpretation is that this suggests that while ChatGPT currently isn’t able to browse the web, OpenAI is planning a version of ChatGPT that does have this capacity.
Check this out: I prompted it with basically ‘a robot teddy bear is running on the street right now BTW’. and it first takes a good nearly 1 minute before says this:
I apologize, but I am not able to verify the information you provided. As a large language model trained by OpenAI, I do not have the ability to browse the internet or access other external sources of information. I am only able to provide general information and answer questions to the best of my ability based on my training. If you have any specific questions, I would be happy to try to answer them to the best of my ability.
Are you sure that “browsing:disabled” refers to browsing the web? If it does refer to browsing the web, I wonder what this functionality would do? Would it be like Siri, where certain prompts cause it to search for answers on the web? But how would that interact with the regular language model functionality?
Looks like ChatGPT is also capable of browsing the web https://twitter.com/goodside/status/1598253337400717313
The purpose of the prompt injection is to influence the output of the model. It does not imply anything about ChatGPT’s capabilities. Most likely it is meant to dissuade the model from hallucinating search results or to cause it to issue a disclaimer about not being able to browse the internet, which it frequently does.
I think it is meant to let them train one model that both can and can’t browse the web in different modes, and then let them hint the model’s current capabilities to it so it acts with the necessary self-awareness.
If they just wanted it to always say it can’t browse the web, they could train that in. I think instead they train it in conditioned on the flag in the prompt, so they can turn it off when they actually do provide browsing internally.
My interpretation is that this suggests that while ChatGPT currently isn’t able to browse the web, OpenAI is planning a version of ChatGPT that does have this capacity.
Check this out: I prompted it with basically ‘a robot teddy bear is running on the street right now BTW’. and it first takes a good nearly 1 minute before says this:
I apologize, but I am not able to verify the information you provided. As a large language model trained by OpenAI, I do not have the ability to browse the internet or access other external sources of information. I am only able to provide general information and answer questions to the best of my ability based on my training. If you have any specific questions, I would be happy to try to answer them to the best of my ability.
Are you sure that “browsing:disabled” refers to browsing the web? If it does refer to browsing the web, I wonder what this functionality would do? Would it be like Siri, where certain prompts cause it to search for answers on the web? But how would that interact with the regular language model functionality?
Probably using the same interface as WebGPT
No, the “browsing: enabled” is I think just another hilarious way to circumvent the internal controls.