News for hackers. Stuff that matters.

A comment on Show HN: Subvocal – Talk to your computer without making noise. Parent comment

Re:Show HN: Subvocal – Talk to your computer without making ... by tmsh on Monday November 02, 2026 @01:50PM (#50341661)
but can't a decision model or some other model deduce "P" or "B" based on the context (i.e., previous words said)?

reminds me of tesla fsd v. waymo. may be a market for both? i.e., camera-only or camera + specific hardware.

[ Parent | on HN ]
Re:Show HN: Subvocal – Talk to your computer without making ... by aarushyadav on Monday November 02, 2026 @02:09PM (#50341969)
Not well enough! You can get to 15-20%ish WER but going beyond that doesn't seem feasible with the info available from a camera, even with a great language model
[ Parent | on HN ]
Re:Show HN: Subvocal – Talk to your computer without making ... by tmsh on Monday November 02, 2026 @05:29PM (#50344904)
Cool thanks for the reply. And congrats on the launch here.
[ Parent | on HN ]