Vowels and diphthongs in sperm whales
1–10 of 32 posts
Re: Vowels and diphthongs in sperm whales
#2I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
Re: Vowels and diphthongs in sperm whales
#3I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
https://youtu.be/hph9OeKjg3w -- here's a video about this about a research effort to accomplish precisely this.
Re: Vowels and diphthongs in sperm whales
#4I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
That’s the kind of task I really want to see LLMs used for - not just to replicate things humans can already do, but to explore things that humans haven’t figured out yet. Maybe we don’t know enough to pick up on the rhyme and reason of whale communication yet, but brute-forcing it with an AI seems like a great way to get a fresh perspective.
Re: Vowels and diphthongs in sperm whales
#5I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
https://www.earthspecies.org/ The motivating intuition was that modern machine learning can build powerful semantic representations of language which we can use to unlock communication with other species.
Re: Vowels and diphthongs in sperm whales
#6I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
Well, lets get an LLM to translate one of the not understood human languages first.
Could we build a chat GPT for whales to use, with this approach, sure. Does that get us any closer to translating it. NO, because without shared context to start building connections and relationships its highly unlikely that were going to find commonality.
Re: Vowels and diphthongs in sperm whales
#7I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
I vaguely remember reading about a research effort into this earlier this year, and I'm positive it wasn't what sp332 linked to. Would be glad if I can find the link.
Re: Vowels and diphthongs in sperm whales
#8I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
Humans finally complete the LLM and attempt to send the first message to a whale.
Humans: “We come in peace. We seek to understand and communicate with you.”
No response.
Humans: “We repeat. We come in peace…”
WhaleGPT: “too late”
Re: Vowels and diphthongs in sperm whales
#9I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
Well, lets get an LLM to translate one of the not understood human languages first. Could we build a chat GPT for whales to use, with this approach, sure. Does that get us any closer to translating it. NO, because without shared context to start building connections and relationships its highly unlikely that were going to find commonality.
>Well, lets get an LLM to translate one of not understood human languages first.
You can do both. Models trained to receive and predict audio tokens alongside text are coming. You could just add such data as part of training.
>Does that get us any closer to translating it. NO, because without shared context to start building connections and relationships its highly unlikely that were going to find commonality.
If you trained it alongside human languages then shared context(if available) will be figured out by the model. They'll coalesce in the same shared space the way they do for human languages. Enough to translate without examples instead of just speak? Perhaps - it's not like there are examples in the training set for every lang to lang combination modern models are capable of translating.
Re: Vowels and diphthongs in sperm whales
#10I can’t help but wonder if we were able to feed a lot of whale communications into LLMs with this new found layer of information if we would be able to translate someday.
https://youtu.be/hph9OeKjg3w -- here's a video about this about a research effort to accomplish precisely this.
What do whales do if we "replay" their sounds?