Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • "He believed that making people fall in love with another species might do more for the ocean than any policy paper ever could."

    This got my wheels turning. Charismatic megafauna (like whales) already drive the top of the funnel for ecological awareness. Imagine what the cetacean equivalent of the staples baddie could do.

    by srvo
  • Communicating with dolphins is much easier than with cachalots, and we have the tech for it at www.dolphinwhispers.com
    by sm001
  • I think understanding the conversation without seeing what the speakers do will be very limiting. The concepts will probably need to be built from the ground https://en.wikipedia.org/wiki/Lincos_language unless we have a large amount of data on which we can train GPT
    by kekqqq
  • I haven’t read the article, but how are they going to do training. The data requires an input along with the outcome and I don’t think this data includes outcomes because it would be near impossible to record and interpret.
    by dyauspitr
  • I love projects. But this reminds me of the model we used in signal and image processing:

    - detection: just separating signal from background with confidence

    - classification: confidently separating different signals in noise (e.g. PCA)

    - identification: requires ground truth (perfect example), but still difficult to do with confidence

    If the scientists have ground truth, e.g. "this call means [xyz]", then it’s a signal processing problem to do identification.

    If there is no ground truth, then AI would have to have a lot of background data on whale activity at different locations including visual and audio content to try to infer (and that's about it) what the vocalization might mean. And this is where science starts to leave the building.

    It's kinda' like inventing the Rosetta Stone using AI: probably not going to be very accurate or repeatable.

    by jschveibinz
  • If they are intelligent and curious, imagine if they let us come tell them tales of the world, works of fiction, musings of space, what if they swim around just letting us tell them of all the fascinating things we find out. Humanity may travel the cosmos, only to come home to tell our whale friends everything we learned. I wonder if there will be a whale someday with the dream of going to space.
    by tednoob
  • I don't want to poopoo this research because I think it's really cool. I just want to urge some caution. There are three distinct risk categories with this research that I think should trigger a halt if certain pre-specified conditions are breached.

    (1) Animal welfare. The researchers are aware of the animal welfare issues at stake, but a collection of metrics around pod culture, stress, and reproduction should be tracked across experiments to make sure we're not hurting the animals. If thresholds are exceeded across multiple experimebts with this tech, the research should stop.

    (2) Acoustic -> semantic gap. There's a green lumber problem with this research. We may be able to predict animal responses in playback tests, but we don't have a way to map that back to semantic meaning. This is probably fine for now, but if we don't have adequate semantic theory or if we have multiple competing semantic theories that all explain the patterns equally well, the we're just manipulating the animals, not communicating with them. (eg, It's not even really clear to me that "whale concepts" and "human concepts" would be commensurable.)

    (3) Bad incentives. Between media sensationalism, the normal problems and biases that come with funding science today, and potentially terrible usages of "whale tech" (eg, clearing out shipping lanes, warfare), it seems to me there are some extra ethical considerations with this research such that there may be a point where the outcome space is overwhelmingly negative. It would be nice if mechanisms existed such that research could be stopped if these bad incentives activate.

    by EarthBlues
  • IMHO translation of anything interesting requires the cultural background for context. To do it with a new language requires the translator to "go native". The mega fauna gets media attention, but they would have more chance of success with one of the many dolphin pods that live up close and personal with humans. For example Shark Bay: https://en.wikipedia.org/wiki/Monkey_Mia In the 1990s we had field linguists interested, but the tech sucked. It's good to try again, but a lit search might help.
    by Peteragain

Explore Birbla archives