alt Hacker NewsClaude Code deletes developers' production setup, including database
Comments
mannyv • today at 4:14 PM
This actually is easy to do with terraform and shared infrastructure; you don't need an AI in the loop.
Who hasn't accidentally deleted a resource because that property triggers a resource delete/create instead of an update?
It would help if it was obvious what the key fields were. But for some reason docs usually don't tell you.
wpm • today at 3:19 PM
"Developers let Claude Code delete their production setup, including database"
Claude Code has no agency. It does what you tell it, where you let it, with a randomized temperature where it might randomly deviate.
rhoopr • today at 3:14 PM
Sloppy vibe infra management and no backups, peanut butter and chocolate.
Yeah, this is what happens when there's nothing between "the agent decided to do this" and "it happened." The agent followed the state file logically. It wasn't wrong. It just wasn't checked.
His post-mortem is solid but I think he's overcorrecting. If he does this as part of a CICD pipeline and he manually reviews every time, he will pretty quickly get "verification fatigue". The vast majority of cases are fine, so he'll build the habit of automatically approving it. Sure, he'll deeply review the first ones, but over time it becomes less because he'll almost always find nothing. Then he'll pay less attention. This is how humans work.
He could automate the "easy" ones, though. TF plans are parseable, so maybe his time would be better spent only reviewing destructive changes. I've been running autonomous agents on production code for a while and this is the pattern that keeps working: start by reviewing everything, notice you're rubber-stamping most of it, then encode the safe cases so you only see the ones that matter.