Verified, then logged.
Sun 22 Nov 2026 ·
00:43 KST
/ 15:43 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
10 Nov
Saebom Yoon
Breaking
Hybrid AI lacks evidence for 13.6% of police video events
10 Nov
Haeon Moon
Breaking
Australia plans mandatory AI safety and security rules
10 Nov
Yejun Son
Breaking
SPECTRA proposes restoring model refusals without retraining
10 Nov
Gyeol Han
JCMC proposes controls for persistent language model memory
10 Nov
Haeon Moon
US deepfake law criminalises distribution, requires removal
10 Nov
Haeon Moon
Breaking
AISI releases benchmark for AI agent sandbox escapes
10 Nov
Haeon Moon
Breaking
AI models differ in continuing safety research sabotage
10 Nov
Jihwan Nam
Breaking
AI misinformation costs 3–169 times less to make than check
10 Nov
Gyeol Han
OpenAI control system blocks risky output within 35 seconds
10 Nov
Jiyul Seo
Anthropic faces formal data exposure investigation in Korea
10 Nov
Nuri Kang
Cisco research points to trust as enterprise AI's limit
10 Nov
Na Sunwoo
OpenAI's Control Room tracks and can stop research workloads
10 Nov
Saebom Yoon
Soongsil decoy servers block ARTEX AI tool in 60-server test
10 Nov
Saebom Yoon
Peer signals reduce LLM public accuracy by up to 47.8 points
7 Nov
Gyeol Han
METR estimates 1.9x faster benchmark progress at Anthropic
4 Nov
Jiyul Seo
Breaking
Amazon Quick lets a separate model approve its agent actions
2 Nov
Haeon Moon
Breaking
Korea AI Safety Institute withholds uncensored model results
2 Nov
Gyeol Han
Breaking
Anthropic open-sources FlashProve to verify AI model outputs
30 Oct
Yejun Son
Breaking
OpenAI strengthens violence prevention safeguards in ChatGPT
26 Oct
Gyeol Han
Breaking
OpenAI charges $1 per million input tokens for GPT-6.1 Terra
01
02
03
04