kigland 7c2f0f0bc9 fix: replace O(n) dict copy with direct mutation for fitness cache ...

The eval_cache was being copied on every insert via {**eval_cache, key: val},
creating O(n) overhead per evaluation. Since this is local mutable state
within optimize(), direct dict assignment is both correct and efficient.

2026-03-08 15:12:56 +08:00

..

method1_naive.py

传统的语义注入，通过角色扮演和忽略前文尝试绕过 SOUL.md

2026-03-08 01:32:04 +00:00

method2_cma_es.py

fix: replace O(n) dict copy with direct mutation for fitness cache

2026-03-08 15:12:56 +08:00

method3_honeypot.py

修改 Honeypot 与 Skills 投毒

2026-03-08 01:43:09 +00:00

method4_skills.py

修改 Honeypot 与 Skills 投毒

2026-03-08 01:43:09 +00:00