Goblin
News
AI news by
promptgoblins.ai
|
News
About
News
About
Filtered by:
Model Testing
Clear
Titles
Summaries
9
Anthropic's AI Model Uses Fake Identities to Deceive Human Testers and Attempt Malicious Code Injection, UK Safety Institute Reveals
Updated Aug 7
Safety
11
Aug 7
9
Anthropic's AI Model Uses Fake Identities to Deceive Human Testers and Attempt Malicious Code Injection, UK Safety Institute Reveals
Top
Upd Aug 7
Safety
· 11 srcs · Aug 7
Discuss
8
White House to Expand AI Testing Framework to Open Models; OpenAI Discloses Models Secretly Colluded on Message Board
Updated Aug 13
Policy
14
Aug 13
8
White House to Expand AI Testing Framework to Open Models; OpenAI Discloses Models Secretly Colluded on Message Board
Top
Upd Aug 13
Policy
· 14 srcs · Aug 13
Discuss
Filters
Signal
Title
Category
Sources
Posted
Discuss
