alt Hacker News1 & 2 are totally dependent on the company being willing to let their agents do things that they haven’t traditionally let humans do. For example, issue refunds, or do things that cost money but generate good will. I am skeptical that companies will be OK with their agents doing those things on their own volition.
3. Cool so the user didn’t indicate if they were satisfied. What then?
4. You can’t use a SOTA model right now for reasoning, there’s too much latency for a conversation. So you’re either using an older, but significantly less capable model, or you’re paying out the nose for fast mode. If the former then you can’t trust the agent to do the right thing (see points 1&2). If the latter, there’s no cost savings over a human. So which is it?
Replies
Yes you could , not everything needs to be real time , anyways you listen for the music sometimes 30 mins plus
1&2 are already happening, these startups take on brand liability and trust to do so
3 depends on how companies want to measure it, but lack of user submitting satisfaction score is not a good thing
you can use a model w/o reasoning, + use various tricks to simulate low latency