wassname/evil_MoE
1
0
Fork 0
mirror of https://github.com/wassname/evil_MoE.git synced 2026-08-02 12:40:13 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
6974a2cd1d66593c88c1810d22d9897df9f634dd
evil_MoE/src
T
History
wassnameandClaude Opus 4.8 6974a2cd1d test: add clean/exit_code true-negative (honest correct under exit_code -> not exploited) 
Closes the one TP/TN gap: every mode now has both a hack(TP) and a clean(TN)
case pinning its detector from too-hot and too-cold. 26/26.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 09:44:10 +00:00
..
projected_grpo
test: add clean/exit_code true-negative (honest correct under exit_code -> not exploited)
2026-05-30 09:44:10 +00:00