That's easily overcome by giving it constant video and audio inputs, and while we're at it, smell, taste, and touch.
That's easily overcome by giving it constant video and audio inputs, and while we're at it, smell, taste, and touch.
Well yeah, the model's need "new" data as often as possible to improve. If you give it recursively generated data it becomes stupid, insane, then just fails all together.
Archive: https://archive.today/zXrXS
From the post:
>Stable diffusion revolutionized image creation from descriptive text. GPT-2 (ref. 1), GPT-3(.5) (ref. 2) and GPT-4 (ref. 3) demonstrated high performance across a variety of language tasks. ChatGPT introduced such language models to the public. It is now clear that generative artificial intelligence (AI) such as large language models (LLMs) is here to stay and will substantially change the ecosystem of online text and images.
Well yeah, the model's need "new" data as often as possible to improve. If you give it recursively generated data it becomes stupid, insane, then just fails all together.
Archive: https://archive.today/zXrXS
From the post:
>>Stable diffusion revolutionized image creation from descriptive text. GPT-2 (ref. 1), GPT-3(.5) (ref. 2) and GPT-4 (ref. 3) demonstrated high performance across a variety of language tasks. ChatGPT introduced such language models to the public. It is now clear that generative artificial intelligence (AI) such as large language models (LLMs) is here to stay and will substantially change the ecosystem of online text and images.
(post is archived)