←back to thread

638 points wut42 | 3 comments | | HN request time: 0.66s | source
Show context
ativzzz ◴[] No.44330627[source]
This is very cool. I think the primary innovation here is twofold:

1. Remote agent - it's a containerized environment where the agent can run loose and do whatever - it doesn't need approval for user tasks because it's in an isolated environment (though it could still accidentally do destructive actions like edit git history). I think this alone is a separate service that needs to be productionized. When I run claude code in my terminal, automatically spin up the agent in an isolated environment (locally or remotely) and have it go wild. Easy to run things in parallel

2. Deep integration with fly. Everyone will be trying to embed AI deep into their product. Instead of having to talk to chatgpt and copy paste output, I should be able to directly interact with whatever product I'm using and interact with my data in the product using tools. In this case, it's deploying my web app

replies(4): >>44330798 #>>44331056 #>>44333082 #>>44334691 #
1. risyachka ◴[] No.44333082[source]
>> Remote agent - it's a containerized environment where the agent can run loose and do whatever

How is this innovation?

replies(1): >>44333122 #
2. kasey_junk ◴[] No.44333122[source]
Many people have not experienced the async agent workflow yet and fairly the major providers didn’t have offerings for them until a month or two ago.

It’s in fact one of my predictors for if they are going to be enthusiastic about agents or not.

And you wouldn’t think containerization would be a big leap but this stuff is so new and moving so fast that combining them with existing tech can surprise people.

replies(1): >>44334208 #
3. throwaway314155 ◴[] No.44334208[source]
It's less innovative and more trendy. A lot of the fly integration can be achieved by simply asking claude code to look up the docs for the fly cli tool.