Re:Anthropic takes $5B from Amazon and pledges $100B in clou...
by CuriouslyC on Tuesday April 21, 2026 @12:51PM
(#47851348)
The only AI use case that cares about latency is interactive voice agents, where you ideally want <200ms response time, and 100ms of network latency kills that. For coding and batch job agents anything under 1s isn't going to matter to the user.
[ Parent
| on HN ]
Re:Anthropic takes $5B from Amazon and pledges $100B in clou...
by electroly on Tuesday April 21, 2026 @01:05PM
(#47851512)
tbh, that's a good point about the voice agents that I hadn't considered. I guess there are some latency-sensitive inference workloads. Thanks for pointing that out.
Re:Anthropic takes $5B from Amazon and pledges $100B in clou...
by devolving-dev on Tuesday April 21, 2026 @01:45PM
(#47852006)
Yeah, also stuff like robotics which might not really exist today but could be big in the future.
Re:Anthropic takes $5B from Amazon and pledges $100B in clou...
by vanviegen on Wednesday April 22, 2026 @02:43AM
(#47859903)
You'll want the time-sensitive parts (motor control) to be running locally anyway.
Re:Anthropic takes $5B from Amazon and pledges $100B in clou...
by coredog64 on Tuesday April 21, 2026 @03:25PM
(#47853346)
A customer service chatbot can require more than one LLM call per response to the point that latency anywhere in the system starts to show up as a degraded end-user experience.