Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12...
by skeledrew on Saturday November 07, 2026 @06:01PM
(#50408877)
You should note that auto-mode is handled by a different session (and likely model) from your actual. There's no road block or deviation or context flooding; all it does is monitor the model actually doing the work and block it from potentially problematic actions (which you can usually override by saying you explicitly give permission for X), nothing more.
[ Parent
| on HN ]
Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12...
by bulder on Saturday November 07, 2026 @06:26PM
(#50409021)
The context pollution happens when a denial triggers but the model still keeps attempting the harmful action via alternative avenues. It's got nothing to do with the auto-mode eval model's actual output.
Re:Claude Code's "Don't Ask Again" exposes passwords in 1,12...
by skeledrew on Sunday November 08, 2026 @07:51AM
(#50412826)
I have never seen that happen before. What I see is a mention that the classifier stopped it from doing X and it then asks for explicit permission or gives me the command to run myself.