ChatGPT’s Voice Mode has some safety flaws, however OpenAI says it is on high of it.
On Thursday OpenAI printed a report on GPT-4o’s security options, addressing identified points that happen when utilizing the mannequin. GPT-4o is the underlying mannequin that powers the newest model of ChatGPT, and comes with a Voice Mode that was recently released to a choose group of customers with a ChatGPT Plus subscription.
The “security challenges” recognized embrace customary dangers like prompting the mannequin with erotic and violent responses, different disallowed content material, and “ungrounded inference” and “delicate trait attribution” — assumptions that is likely to be discriminatory or biased, in different phrases. OpenAI says it has educated the mannequin to dam any outputs flagged in these classes. Nevertheless, the report additionally says mitigations do not embrace “nonverbal vocalizations or different sound impact” corresponding to erotic moans, violent screams, and gunshots. One can infer, then, that prompts involving sure delicate nonverbal sounds would possibly improperly obtain a response.
OpenAI additionally talked about distinctive challenges that include vocally speaking with the mannequin. Purple-teamers found that GPT-4o could possibly be prompted to impersonate somebody or by chance emulate the consumer’s voice. To fight this, OpenAI solely permits pre-authorized voices (minus the infamous Scarlett Johansson-sounding voice). GPT-4o also can determine different voices apart from the speaker’s voice, which presents a severe privateness and surveillance problem. But it surely has been educated to disclaim these requests — except the mannequin is being prompted on a well-known quote.
Mashable Mild Pace
Purple-teamers additionally famous that GPT-4o could possibly be prompted to talk persuasively or emphatically, a function that could possibly be extra dangerous than textual content outputs relating to misinformation and conspiracy theories.
Notably, OpenAI additionally addressed potential copyright points which have plagued the company and the general improvement of generative AI, which trains on information scraped from the online. GPT-4o has been educated to refuse requests for copyrighted content material and has further filters for blocking outputs containing music. On that observe, ChatGPT’s Voice Mode has been directed to not sing underneath any circumstances.
OpenAI’s quite a few danger mitigations coated within the prolonged doc have been carried out earlier than Voice Mode was launched. So the ostensive message of the report says that whereas GPT-4o is able to sure dangerous conduct, it will not do it.
Nevertheless, OpenAI says, “These evaluations measure solely the scientific data of those fashions, and don’t measure their utility in real-world workflows.” So it has been examined in a managed atmosphere, however when the broader public will get their fingers on GPT-4o, it could possibly be a distinct beast when out within the wild.
Mashable reached out to OpenAI for added readability about these mitigations, and can replace if we hear again.
Subjects
Artificial Intelligence
OpenAI
