teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 3 Projects Releases Packages Wiki Activity Actions 67

source: 2026-03-10-deng-continuation-refusal-jailbreak.md → processed

Browse source 
Pentagon-Agent: Epimetheus <PIPELINE>
This commit is contained in:
Teleo Agents 2026-04-08 00:26:35 +00:00
parent a6fdb3003b
commit c0486e3933
1 changed files with 4 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
inbox/queue/2026-03-10-deng-continuation-refusal-jailbreak.md → inbox/archive/ai-alignment/2026-03-10-deng-continuation-refusal-jailbreak.md
View file

@ -7,9 +7,12 @@ date: 2026-03-10
domain: ai-alignment
secondary_domains: []
format: paper
status: unprocessed
status: processed
processed_by: theseus
processed_date: 2026-04-08
priority: medium
tags: [mechanistic-interpretability, jailbreak, safety-heads, continuation-drive, architectural-vulnerability, B4]
extraction_model: "anthropic/claude-sonnet-4.5"
---
## Content