← All IntelClip / EntertainmentParallelization is model/prompt work, not user work
From Anthropic's Boris Cherny: Why Coding Is Solved, and What Comes Next · ≈19:51
“Hey, I noticed that the data is changing over time. I'll start a loop and I'll give you a report every 30 minutes.”
“So I think actually over time, it's not on users to figure out how to hold the tools better.”
What’s in it
- Hear how model improvements auto-enable parallel sub-agents without extra prompting
- See a real example of an agent self-starting a monitoring loop
- Learn why agent usability is a model and prompting problem, not the user's
Clip transcript
can spin up 10 sub agents for something. Yeah, I mean on on the product side, it really just comes down to prompting. That's That's how it is. And so, you know, we we tweak prompts to kind of help the model do stuff in parallel more. But also, honestly, as the model gets better, it just naturally does this. And so, something like loop, I found actually 4.7, it just starts doing. Uh which is really cool. It's like it does something like uh you know, I'll I'll I'll tell it, "Go uh pull this data query." And it's like, "Hey, I noticed that the data is changing over time. I'll start a loop and I'll give you a report every 30 minutes." And I'm like, "Great. Can you send it to me over Slack?" And then it uses the Slack MCP to do that. So, so I think actually over time, it's not on users to figure out how to hold the tools better. And if that's the case, it's actually a product design problem and like I'm not doing a good job. It's really on the model to do this stuff better and on us kind of prompting
Comments
Sign in to comment.
Loading comments…