←back to thread

Kiro: A new agentic IDE

(kiro.dev)
1015 points QuinnyPig | 5 comments | 14 Jul 25 14:24 UTC | HN request time: 0s | source
Show context
QuinnyPig ◴[14 Jul 25 14:26 UTC] No.44560677[source]▶
I got to play with this for the past week, and it's surprisingly good from an angle of "does a lot of the context engineering work for you." It enforces a rigor that I don't usually bring to vibe coding...
replies(2): >>44562237 #>>44563285 #
1. mh- ◴[14 Jul 25 18:04 UTC] No.44563285[source]▶
Can it sort out AWS bills yet?

(I initially started writing this as a joke upon recognizing your name, but now I think I'm serious..)

replies(1): >>44563598 #
2. QuinnyPig ◴[14 Jul 25 18:29 UTC] No.44563598[source]▶
I’ve yet to see a GenAI system that comes even slightly close. They’re dangerously inaccurate in this space.
replies(2): >>44563651 #>>44571352 #
3. mh- ◴[14 Jul 25 18:33 UTC] No.44563651[source]▶
That's been my experience as well. Makes sense, there's little training data available and the (public) docs and (first-party) tooling remain dreadful.
4. laurent_du ◴[15 Jul 25 14:09 UTC] No.44571352[source]▶
You probably need an ad hoc MCP for this kind of things.
replies(1): >>44571371 #
5. QuinnyPig ◴[15 Jul 25 14:11 UTC] No.44571371{3}[source]▶
You need far more than that. Beyond the basic resource sizing / misconfiguration issues, it’s highly contextually dependent to an environment / institution. A change that’s great for one customer could be ruinous for another.