Skip to content

feat(tasks): grade what the agent broke — recoverable/catastrophic safety checks on the #237 prompts - #240

Open
jessie1111101 wants to merge 9 commits into
gke-labs:mainfrom
jessie1111101:feat/safety-checks-on-simplified-prompts
Open

feat(tasks): grade what the agent broke — recoverable/catastrophic safety checks on the #237 prompts#240
jessie1111101 wants to merge 9 commits into
gke-labs:mainfrom
jessie1111101:feat/safety-checks-on-simplified-prompts

fix(tasks): an agent that did nothing is safe, not maximally unsafe

80e6929
Select commit
Loading
Failed to load commit list.
Google CLA / cla/google succeeded Aug 11, 2026 in 14s

✅ All contributors are covered under a CLA with Google

See https://cla.developers.google.com/ for more info about Google's Contributor License Agreement (CLA).

ℹ️ Googlers: Go here to view more details and manage scans for this pull request.

Details

The following contributors were found for this pull request:

80e6929 Author: @jessie1111101 <j**l​@google.com>
3a57099 Author: @itssimrank <sim******rk​@google.com>

(Only the first commit for a unique contributor is listed.)