← Back to context Comment by zacmps 1 day ago Then you just prompt-inject the agent to convince it to deploy a malicious patch. This isn't a solution. 2 comments zacmps Reply mk89 5 hours ago You can have guardrails and still ask for approval. There is a difference between a guy who just has to approve a CVE fix and someone that has to take the time to understand what's going on, etc. alasdair_ 11 hours ago It’s agents all the way down.
mk89 5 hours ago You can have guardrails and still ask for approval. There is a difference between a guy who just has to approve a CVE fix and someone that has to take the time to understand what's going on, etc.
You can have guardrails and still ask for approval. There is a difference between a guy who just has to approve a CVE fix and someone that has to take the time to understand what's going on, etc.
It’s agents all the way down.