AI interpretability leads to discovery of vowels in sperm whale language
begusgasper · x · 2026-08-26
This study showcases AI interpretability directly leading to a scientific discovery. Researchers built an 'artificial baby model' that learns language directly from raw sounds to imitate sperm whale speech. By examining the model's internals, they recovered known biological properties and identified previously overlooked features. This initial clue eventually led to the discovery of vowels in sperm whale communication, suggesting that reframing language through AI can help bypass human biases and reveal new realities about nature.
More from Research
- Pathway CSO pitches BDH as post-Transformer architecture uniting memory, reasoning, adaptation — schwentker · 2026-10-15
- EmbodiedEvo tops RoboDojo at 38.95% success by letting robots inherit failed practice — thetripathi58 · 2026-10-15
- 797GB of n-gram counts in CPU RAM let 1B models match 57% more compute — PangWeiKoh · 2026-10-15
- Google's HARNESS² evolves agent harnesses without verifiers, up to +11.5 points on WorkBuddy-Bench — dair_ai · 2026-10-15
- Subbarao Kambhampati to dissect the 'mythos of LLM thinking tokens' at UMN — rao2z · 2026-10-15
- How 3D Gaussian Splatting gives robots spatial memory of what's out of view — TheTuringPost · 2026-10-15