<div dir="ltr"><div dir="ltr"><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, 18 May 2026 at 04:32, Stuart LaForge via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org" target="_blank">extropy-chat@lists.extropy.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">In Douglas Adam's "Hitchhiker's Guide to the Galaxy" the babelfish are <br>
small fish that when placed in ones ear, translated all languages for <br>
the wearer. Amazingly over the past few years, LLM have been used to <br>
used like Babelfish or a universal translator between several of the <br>
most intelligent species on Earth. In the past year, the scientists of <br>
CETI have trained LLMs by unsupervised learning on hours of recorded <br>
sperm whale vocalizations and upon analysis discovered that they possess <br>
a rich phonetic alphabet replete with vowels and diphthongs.<br>
<br>
<a href="https://direct.mit.edu/opmi/article/doi/10.1162/OPMI.a.252/133906/Vowel-and-Diphthong-Like-Spectral-Patterns-in" rel="noreferrer" target="_blank">https://direct.mit.edu/opmi/article/doi/10.1162/OPMI.a.252/133906/Vowel-and-Diphthong-Like-Spectral-Patterns-in</a><br>
<br>
Google Deepmind has trained Dolphin Gemma, a dolphin-specific large <br>
language model and is developing a wearable diver's interface that would <br>
allow divers to use Dolphin Gemma communicate in real time with Dolphins <br>
with while swimming.<br>
<br>
<a href="https://deepmind.google/models/gemma/dolphingemma/" rel="noreferrer" target="_blank">https://deepmind.google/models/gemma/dolphingemma/</a><br>
<br>
And on land, scientists have used LLMs to figure out that wild African <br>
bush elephants have distinctive names for each member of the herd and <br>
playing their name over over the loudspeaker causes the named elephant <br>
and only the named elephant to respond.<br>
<br>
<a href="https://www.nature.com/articles/s41559-024-02420-w.epdf" rel="noreferrer" target="_blank">https://www.nature.com/articles/s41559-024-02420-w.epdf</a><br>
<br>
The notion that artificial intelligence could act as bridge between <br>
biological intelligences of all species is something that is not often <br>
brought up in the current debates about alignment and safety.<br>
<br>
Stuart LaForge<br>
_______________________________________________<br></blockquote><div><br></div><br></div><div class="gmail_quote"><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default"><br></div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">I asked Gemini AI if this implied some level of consciousness in animals.</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">Gemini said probably yes, but pointed out that AIs themselves can produce context-aware responses without being conscious.</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">This seems to imply that AIs will soon add the missing requirements to become fully conscious.</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">Interesting? Full Gemini response below.</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">BilllK</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default"><br></div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">Gemini 3.1 Thinking - </div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default"><span><div id="m_298594606184035299gmail-chat-history"><span><div id="m_298594606184035299gmail-4989e1183bc7b868" style="min-height:261px"><span><div><span><div><div><div><span></span></div><div><div><div><div><div><span style="height:auto"></span></div></div></div><span style="height:auto"><div><span id="m_298594606184035299gmail-message-content-id-r_4989e1183bc7b868"><div id="m_298594606184035299gmail-model-response-message-contentr_4989e1183bc7b868" dir="ltr"><p>The short answer is <b>yes, it heavily implies it</b>—at least by the standards of modern cognitive ethology and philosophy of mind.</p><p>For centuries, human exceptionalism relied on the argument that because animals lacked structured language, they lacked abstract thought, and therefore lacked a complex internal life. René Descartes famously dismissed animals as mere <i>automata</i>—flesh-and-blood machines responding purely to mechanical stimuli.</p><p>By using AI to strip away our own sensory biases, we are discovering that animal communication isn’t just a series of reflexive, emotional outbursts (like a yelp of pain or a purr of pleasure). It features structural syntax, contextual negotiation, and intentionality.</p><p>Here is how these AI breakthroughs translate into the debate over animal consciousness:</p><hr><h2>1. Shattering the "Stimulus-Response" Myth</h2><p>Consciousness requires a degree of representation—the ability to hold a map of the world, your peers, and yourself in your mind.</p><p>When AI models analyze the communication of bats arguing over specific sleeping spaces, or sperm whales adjusting the "rubato" (timing) of their clicks to duet with a specific partner, it demonstrates <b>intentionality</b>. The animals are not just reacting to an immediate physical stimulus; they are navigating complex social landscapes, recalling past interactions, and projecting future intent. This level of cognitive flexibility is incredibly difficult to explain without attributing some form of subjective, conscious experience to the agent.</p><h2>2. The Scientific Consensus Has Already Shifted</h2><p id="m_298594606184035299gmail-p-rc_c78c75e4a280e6f0-37"><span>The idea of animal consciousness is no longer a fringe, romantic notion; it is the baseline scientific consensus.<span></span></span><span> <span></span></span></p><p id="m_298594606184035299gmail-p-rc_c78c75e4a280e6f0-38">A major milestone occurred with the release of <b>The New York Declaration on Animal Consciousness</b>. <span>Signed by a massive coalition of the world's leading neuroscientists, animal cognitivists, and philosophers (including thinkers like David Chalmers and Anil Seth), the declaration established a clear framework:<span></span></span><span> <span></span></span></p><ul><li><p id="m_298594606184035299gmail-p-rc_c78c75e4a280e6f0-39"><span>There is </span><b><span>strong scientific support</span></b><span> for conscious experience (sentience/qualia) in mammals and birds.<span></span></span><span> <span></span></span></p></li><li><p id="m_298594606184035299gmail-p-rc_c78c75e4a280e6f0-40"><span>There is a </span><b><span>realistic possibility</span></b><span> of conscious experience in all vertebrates (including reptiles, amphibians, and fish) and many invertebrates (like octopuses, decapod crustaceans, and insects).<span></span></span><span> <span></span></span></p></li></ul><p>The AI linguistic data we are gathering now serves as the empirical scaffolding supporting this declaration.</p><h2>3. The "LLM Paradox" (The Skeptical Counter-Argument)</h2><p>To remain strictly analytical, there is a fascinating counter-argument that mirrors our current debates over artificial intelligence itself.</p><p>A skeptic could argue: <i>Large Language Models generate incredibly complex, syntactically perfect, and context-aware responses, yet they are not conscious. Why couldn't a sperm whale's coda system be a highly optimized, biologically evolved algorithm that outputs complex acoustic data without requiring a "light on inside" (phenomenal consciousness)?</i></p><p>The reason biologists lean toward consciousness rather than mere biological algorithms comes down to the <b>multimodal context</b>. We aren't just seeing complex sounds in a vacuum; we are seeing those sounds explicitly paired with complex behaviors—grief rituals, tool use, tactical play, problem-solving, and distinct individual personalities. The communication is the <i>expression</i> of an internal state, not just an automated output.</p><hr><blockquote><p><b>The Takeaway:</b> AI isn't <i>granting</i> animals consciousness; it is correcting human hearing. It functions as a cognitive bridge, proving that non-human minds are processing a rich, subjective version of reality.</p></blockquote><p>If different species—separated by millions of years of evolution—are using highly structured communication to map out and negotiate their shared realities, what do you think this suggests about how intelligence and internal models of the world naturally converge across the tree of life?</p><p>----------------------------------------------</p></div></span></div></span><div><span><span><div><span></span></div></span></span></div></div><span></span></div></div><div><span><div><div><span></span><span></span><div><span></span></div><span></span></div></div></span></div></div></span><span></span></div></span><span></span><span></span></div></span></div></span><br></div></div></div>
</div>