Development
A model reads silent speech from ultrasound of the tongue
Claim
Aleph trained a model to read silent speech from ultrasound of the tongue at a 15.6% error rate after just 50 hours of data, while Würzburg researchers found the ants that amputate injured nestmates' legs are not specialist surgeons but foragers in transition, with care falling to whoever is socially closest.
Reported metric: 15.6% error / 50 hrs
Reporting date: (not necessarily the event date)
Sources
Attribution and reporting linked by this record; links do not imply independent verification.
- Welcome to July 8, 2026 (theinnermostloop.substack.com)
Knowledge graphopen in browser →
Reported in
Cite or correct this record
Suggest a correction — opens a GitHub draft for you to review and submit.