News for hackers. Stuff that matters.

A comment on Show HN: Sparrow-1 – Audio-native model for human-level turn-taking without ASR. Parent comment

Re:Show HN: Sparrow-1 – Audio-native model for human-level t... by fudged71 on Thursday January 15, 2026 @01:23AM (#46628775)
Different industry, but our marketing guy once said "You know what this [perfect] metric means? We can never use it in marketing because it's not believable"
[ Parent | on HN ]
Re:Show HN: Sparrow-1 – Audio-native model for human-level t... by khalic on Thursday January 15, 2026 @02:12AM (#46629143)
Just include some noise, it’s like the most available resource in the universe
[ Parent | on HN ]
Re:Show HN: Sparrow-1 – Audio-native model for human-level t... by drob518 on Thursday January 15, 2026 @07:05AM (#46631311)
Never thought of noise as a resource, but yea.
[ Parent | on HN ]