TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

DolphinGemma: How Google AI is helping decode dolphin communication

324 pointsby alphabettingabout 2 months ago

22 comments

canyon289about 2 months ago
I work at Google on the Gemma team, and while not on the core team for this model, participated a bit on this project.<p>I personally was happy to see this project get built. The dolphin researchers have been doing great science for years, from the computational&#x2F;mathematics side it was quite neat see how that was combined with the Gemma models.
评论 #43686609 未加载
Imnimoabout 2 months ago
This sounds very cool at a conceptual level, but the article left me in the dark about what they&#x27;re actually doing with DolphinGemma. The closest to an answer is:<p>&gt;By identifying recurring sound patterns, clusters and reliable sequences, the model can help researchers uncover hidden structures and potential meanings within the dolphins&#x27; natural communication — a task previously requiring immense human effort.<p>But this doesn&#x27;t really tell me anything. What does it mean to &quot;help researchers uncover&quot; this stuff? What is the model actually <i>doing</i>?
评论 #43684654 未加载
xnxabout 2 months ago
Cool to see the use of consumer phones as part of the setup. Having a suite of powerful sensors, processing, display, and battery in a single, compact, sealed package must be immensely useful for science.
lukevabout 2 months ago
Tangential, but this brings up a really interesting question for me.<p>LLMs are multi-lingual without really trying assuming the languages in question are sufficiently well-represented in their training corpus.<p>I presume their ability to translate comes from the fact that there are lots of human-translated passages in their corpus; the same work in multiple languages, which lets them figure out the necessary mappings between semantic points (words.)<p>But I wonder about the translation capability of a model trained on multiple languages but with completely disjoint documents (no documents that were translations of another, no dictionaries, etc).<p>Could the emerging latent &quot;concept space&quot; of two completely different human languages be similar enough that the model could translate well, even without ever seeing examples of how a multilingual human would do a translation?<p>I don&#x27;t have a strong intuition here but it seems plausible. And if so, that&#x27;s remarkable because that&#x27;s basically a science-fiction babelfish or universal translator.
评论 #43687806 未加载
评论 #43687288 未加载
评论 #43684653 未加载
ZeroCool2uabout 2 months ago
Wow, there&#x27;s a lot of cynicism in this thread, even for HN.<p>Regardless of whether or not it works perfectly, surely we can all relate to the childhood desire to &#x27;speak&#x27; to animals at one point or another?<p>You can call it a waste of resources or someones desperate attempt at keeping their job if you want, but these are marine biologists. I imagine cross species communication would be a major achievement and seems like a worthwhile endeavor to me.
评论 #43684404 未加载
评论 #43684439 未加载
评论 #43683126 未加载
评论 #43685739 未加载
评论 #43684388 未加载
评论 #43684208 未加载
评论 #43684151 未加载
评论 #43690799 未加载
评论 #43689215 未加载
评论 #43683213 未加载
评论 #43683469 未加载
engineer_22about 2 months ago
This crowd seems to be cross pollinated with the sci-fi &#x2F; space exploration set. Communication with cetaceans seems like such an obvious springboard for developing frameworks and techniques for first contact with E.T. &#x2F;If&#x2F; you believe they&#x27;re out there... And if not, what an incredible opportunity in its own right.<p>But, since context is so important to communication, I think this would be easier to accomplish with carefully built experiments with captive dolphin populations first. Beginning with wild dolphins is like dropping a guy from New York City into rural Mongolia and hoping he&#x27;ll learn the language.
summerlightabout 2 months ago
I wonder what&#x27;s the status quo on the non-LLM side; are we able to manually decode sound patterns to recognize dolphin&#x27;s communication to some degree? If that&#x27;s the case, I guess this may have a chance.
tplabout 2 months ago
The experiment design sounds pretty cool. I hope they see some cool results. It would be very cool if humans could talk to another intelligent creature here on earth. This is certainly a step on the way there.
meindnochabout 2 months ago
If only John C. Lilly was alive...
nikolayasdf123about 2 months ago
so, did it work?... anyone knows what is the result of this work?
评论 #43682856 未加载
oulipoabout 2 months ago
My secret wish is that once they decode the language, they hear the dolphin say to themselves: look, it&#x27;s again those idiot humans trying to bother us, why can&#x27;t they just live happily like we do?<p>And then the world will suddenly understand...
dclabout 2 months ago
Wouldn&#x27;t have even been a believable April fools joke even 5 years ago.
floridianfisherabout 2 months ago
The application of modern LLM technology to animal communication is exciting.
sreanabout 2 months ago
Can a powerful model become a fantastic autocomplete for dolphins ? Sure. Someday soon that&#x27;s very likely to happen. But that alone would tell us almost nothing of what dolphin dialogue means.<p>To understand their language we need shared experiences, shared emotions, common internal worlds. Observation of dolphin-dolphin interaction would help but to a limited degree.<p>It would help if the dolphins are also interested in teaching us. Dolphins or we could say to the other &#x27;... that is how we pronounce sea-cucumber&#x27;. Shared nouns would be the easiest.<p>The next level, a far harder level, would be to reach the stage where we can say &#x27;the emotion that you are feeling now, that we call &quot;anger&quot;&#x27;.<p>We will no quite have the right word for &quot;anxiety that I feel when my baby&#x27;s blood flow doesn&#x27;t sound right in Doppler&quot;.<p>Teaching or learning &#x27;ennui&#x27; and &#x27;schadenfreude&#x27; would be a whole lot harder.<p>This begs a question can one fully feel and understand an emotion we do not have a word for ? Perhaps Wittgenstein has an answer.<p>Postscript: I seem to have triggered quite a few of you and that has me surprised. I thought this would be neither controversial nor unpopular. It&#x27;s ironic in a way. If we can&#x27;t understand each other, understanding dolphin &quot;speech&quot; would be a tough hill to climb.
评论 #43683646 未加载
评论 #43682708 未加载
评论 #43682753 未加载
评论 #43682964 未加载
neuroelectronabout 2 months ago
SeaQuest anyone? I still have the first comic.
评论 #43683823 未加载
zoogenyabout 2 months ago
Not directly related, but one of those stories that is so bizarre you almost can&#x27;t believe it isn&#x27;t made up.<p>There was a NASA funded attempt to communicate with Dolphins. This eccentric scientist created a house that was half water (a series of connected pools) and half dry spaces. A woman named Margaret Howe Lovatt lived full-time with the Dolphins attempting to learn a shared language between them.<p>Things went completely off the rails in many, many ways. The lead scientist became obsessed with LSD and built an isolation chamber above the house. This was like the sensory deprivation tanks you get now (often called float tanks). He would take LSD and place himself in the tank and believed he was psychically communicating with the Dolphins.<p>1. <a href="https:&#x2F;&#x2F;www.theguardian.com&#x2F;environment&#x2F;2014&#x2F;jun&#x2F;08&#x2F;the-dolphin-who-loved-me" rel="nofollow">https:&#x2F;&#x2F;www.theguardian.com&#x2F;environment&#x2F;2014&#x2F;jun&#x2F;08&#x2F;the-dolp...</a>
评论 #43690485 未加载
评论 #43685684 未加载
评论 #43699667 未加载
评论 #43690800 未加载
评论 #43685236 未加载
sarrephabout 2 months ago
I’m pretty sure by the time we decode what they’re saying it’ll be “so long, and thanks for all the fish”
评论 #43683726 未加载
givemeethekeysabout 2 months ago
&quot;Lies Dolphins Said About Orcas&quot; - the tell-all book about how Orcas went extinct &#x2F;s
rcarmoabout 2 months ago
The only output I&#x27;ll believe from this is &quot;So long, and thanks for all the fish!&quot;
评论 #43684384 未加载
nightflyabout 2 months ago
&quot;Matthews... we&#x27;re getting another one of those strange &#x27;aw blah es span yol&#x27; sounds.&quot;
xenaabout 2 months ago
This looks like a marine biologist desperately wanted to keep their job in spite of the &quot;nothing that&#x27;s not AI&quot; mandate so they made up some bullshit.
评论 #43683151 未加载
评论 #43684352 未加载
palashkulshabout 2 months ago
Was I the only one who thought it was related to dolphin uncensored models over gemma