Ep. 1 - Awni Hannun on ASR, MLX and the future of on-device AI episode artwork

EPISODE · Mar 15, 2026 · 1H 2M

Ep. 1 - Awni Hannun on ASR, MLX and the future of on-device AI

from localhost · host Atila

Atila Orhon, founder of Argmax, locally hosts Awni Hannun, co-creator of MLX:(00:00) AlexNet moment for Speech(03:50) Baidu Mafia(07:34) Grading Awni's 2021 predictions for 2030(22:08) Personalizing ASR for mainstream adoption(32:45) MLX(35:35) From research tool to inference engine(40:05) On-device AI for enthusiast users vs developer default(45:27) Open-source philosophy(51:05) Why did MLX expand to CUDA?(55:45) After MLX(56:36) Intelligence per watt(01:01:13) Advice for researchers on negative results

Episode metadata supplied by the publisher feed · Published Mar 15, 2026

Embed this episode

NOW PLAYING

Ep. 1 - Awni Hannun on ASR, MLX and the future of on-device AI

0:00 1:02:55

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of localhost?

This episode is 1 hour and 2 minutes long.

When was this localhost episode published?

This episode was published on March 15, 2026.

Can I download this localhost episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!