Researchers are utilizing large language models to explore and decode the communication patterns of animals, with initiatives like Google DeepMind's DolphinGemma allowing scientists to study dolphin sounds. This project aims to understand and communicate back with dolphins, and it collaborates with organizations such as Georgia Tech and the Wild Dolphin Project. Drew Purves of DeepMind believes these advancements could bridge information gaps and enhance our relationship with nature, while the Earth Species Project continues to develop the world's first large audio-language model for animal sounds, called NatureLM-audio.
"I like to think that we will be able to talk to animals at some point," Drew Purves, the nature lead at Google DeepMind, said on a recent episode of the company's podcast.
"It takes the sounds, separates them out, tokenizes them, and basically brings it into the world of large language modeling," Purves said.
"Most of what we're doing at the moment, as I mentioned, is filling known information gaps," he said.
"Sometimes, you think that the real change can come, in the long run, from these, these moments of awakening, where people almost overnight can change their relationship with nature."
#animal-communication #ai-and-machine-learning #dolphins #large-language-models #earth-species-project
Collection
[
|
...
]