Verified, then logged.
Sun 22 Nov 2026 ·
00:28 KST
/ 15:28 UTC
한국어
|
EN
Search /
Home
AI
IT
Hardware
Policy
Contests
Showcase
Tag · Topic
AI safety
Articles and logged changes tagged AI safety.
68 in total
ai-safety
21 Nov
Doyun Lee
Breaking
Contrastive learning improves AI jailbreak detection
21 Nov
Gyeol Han
Breaking
Internal signals detect medical AI manipulation more often
20 Nov
Jiyul Seo
Praxi-Bot sets out a design for approving model tool actions
20 Nov
Yejun Son
Breaking
New rule cuts false safety approvals in gallbladder surgery
20 Nov
Yejun Son
Breaking
Structured records flag the same missing results as answers
20 Nov
Saebom Yoon
Ex-Anthropic researcher criticises AI work by big businesses
20 Nov
Saebom Yoon
Breaking
Databricks outlines 4 AI agent designs for regulated sectors
20 Nov
Jihwan Nam
Breaking
A logo changes AI responses to visible and infrared images
20 Nov
Chaewoo Lim
Breaking
Review urges reasoning audits for medical AI certification
17 Nov
Narae Keum
Web course covers AI agent creation and control
17 Nov
Narae Keum
AI agent control extends to tools, files and task execution
17 Nov
Daon Jeong
Language model edits depend on evaluation conditions
16 Nov
Haram Do
Fewer bird-deterrent responses leave crop protection unclear
16 Nov
Gyeol Han
Breaking
sra-riskgate totals wallet spending across chains
16 Nov
Sebin Oh
Breaking
AgentRisk opens team registration for risk assessment
16 Nov
Minjae Cha
AI design approach puts control into system architecture
15 Nov
Haeon Moon
Carnegie researchers propose checks on non-public AI
14 Nov
Yejun Son
Anthropic proposes safety tests for whole conversations
14 Nov
Gyeol Han
Breaking
PREWARN separates failure detection from early warning
14 Nov
Gyeol Han
Breaking
Classifier outperforms model at detecting perturbations
01
02
03
04