Hacker News new | ask | show | jobs
by ceejayoz 2 days ago
Sure. Claude does that. "Cogitated for 1m 50s" doesn't work for real-time applications.
1 comments
charcircuit 2 days ago
You can submit many queries in parallel to increase throughout. Smaller models and faster hardware can reduce the time per query too.
link
ceejayoz 2 days ago
None of that gets you the 100ms response time the parent poster talked about, for something like "who is at my doorbell?" real-time uses.
link
sebmellen 2 days ago
Ok. Claude will not work for this use case because none of the sample data (weirdly blurry ID images) is in the training data.
link