| ▲ | arjie 6 hours ago |
| I have never found any utility in that. After all, you can still just review the diffs and ask it for explanation for sections instead. |
|
| ▲ | pavel_lishin 6 hours ago | parent | next [-] |
| > After all, you can still just review the diffs anonu has explicitly said that they've wiped a database twice as a result of agents doing stuff. What sort of diff would help against an agent running commands, without your approval? |
| |
| ▲ | arjie an hour ago | parent | next [-] | | Agent does not have to run in your user context. It is easy mistake to make in yolo mode but after that it's easy to fix. e.g. this is what I use now so I can release agent from my machine and also constrain its access: $ main-app git:(main) kubectl get pods | grep agent | head -n 1 | sed -E 's/[a-z]+-agent(.*)/app-agent\1/'
app-agent-656c6ff85d-p86t8 1/1 Running 0 13d
Agent is fully capable of making PR etc. if you provide appropriate tooling. It wipes DB but DB is just separate ephemeral pod. One day perhaps it will find 0-day and break out, but so far it has not done it. | |
| ▲ | exe34 5 hours ago | parent | prev [-] | | Hah I run my agent inside a docker with just the code. Anything clever it tries to do just goes nowhere. |
|
|
| ▲ | ModernMech 5 hours ago | parent | prev [-] |
| > After all, you can still just review the diffs The diff: +8000 -4000 |
| |
| ▲ | arjie 44 minutes ago | parent [-] | | You can ask it to make the changes in appropriate PRs. SOTA model + harness can do it. I find it useful to separate refactors and implementations, just like with humans, but I admittedly rely heavily on multi-provider review. |
|
