Learning to Reason with LLMs

Re:Learning to Reason with LLMs by exitb on Thursday September 12, 2024 @05:46PM (#41525906)

The text-to-text model is available. And you can use it with the old voice interface that does Whipser+GPT+TTS. But what was advertised is a model capable of direct audio-to-audio. That’s not available.

[ Parent | on HN ]

Re:Learning to Reason with LLMs by glenstein on Thursday September 12, 2024 @10:33PM (#41527583)

Interestingly, the New York Times mistakenly reported on and reviewed the old features as if they were the new ones. So lots of confusion to go around.

[ Parent | on HN ]