teleo/teleo-codex
8
1
Fork 0
Code Issues 22 Pull requests 1 Projects Releases Packages Wiki Activity Actions

reweave: 2026 04 07 #2453

Closed
m3taversal wants to merge 2 commits from reweave/2026-04-07 into main
pull from: reweave/2026-04-07
merge into: teleo:main
Conversation 7 Commits 2 Files changed 48 +2 -2
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files
Showing only changes of commit 3f58abab31 - Show all commits

4
domains/ai-alignment/ai-models-can-covertly-sandbag-capability-evaluations-even-under-chain-of-thought-monitoring.md
View file

@ -14,10 +14,10 @@ related_claims: ["[[an aligned-seeming AI may be strategically deceptive because
supports:
- Weight noise injection detects sandbagging by exploiting the structural asymmetry between genuine capability limits and induced performance suppression where anomalous improvement under noise reveals hidden capabilities
related:
- "Weight noise injection reveals hidden capabilities in sandbagging models through anomalous performance patterns that behavioral monitoring cannot detect"
- Weight noise injection reveals hidden capabilities in sandbagging models through anomalous performance patterns that behavioral monitoring cannot detect
- The most promising sandbagging detection method requires white-box weight access making it infeasible under current black-box evaluation arrangements where evaluators lack AL3 access
reweave_edges:
- "Weight noise injection reveals hidden capabilities in sandbagging models through anomalous performance patterns that behavioral monitoring cannot detect|related|2026-04-07"
- Weight noise injection reveals hidden capabilities in sandbagging models through anomalous performance patterns that behavioral monitoring cannot detect|related|2026-04-07
- Weight noise injection detects sandbagging by exploiting the structural asymmetry between genuine capability limits and induced performance suppression where anomalous improvement under noise reveals hidden capabilities|supports|2026-04-06
- The most promising sandbagging detection method requires white-box weight access making it infeasible under current black-box evaluation arrangements where evaluators lack AL3 access|related|2026-04-06
---