The InfoQ Podcast · The Future of Web Apps: Will AI Agents Generate UIs on the Fly?
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
asserted that local-first models are not always lower latency than remote APIs
“Closing the first meeting with an assertive assumption rather than asking if the prospect has any questions increases the chances the prospect will schedule a second meeting”
“We've distributed easily more than 30-40 million dollars worth of compute access and credits for different API models”
“Latency is like 20 to 30 milliseconds for first read on hard disk… on SSD it gets down to closer to SSD latencies… 30 microseconds, 50 microseconds.”
“The call we had because he was remote. We did a Google Meet call. It lasted less than two minutes… I had a script… went through all the details… it was very quick.”
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.