News for hackers. Stuff that matters.
Re:Neural audio codecs: how to get audio into LLMs by smusamashah on Tuesday October 21, 2025 @04:35PM (#45661357)
There was an example, of ChatGPT copying and responding in the speakers voice mid conversation, on OpenAI blog. This was presented an example on non-alignment.

There are no comments on this comment yet.