Alignment Faking in AI: Even LLM can lie !
Tags
attack-pattern: Data Model Models Vulnerabilities - T1588.006
Show in Graph
Common Information
Type Value
UUID 1f5b5c97-cc8f-4291-a7f8-b0866b5063d5
Fingerprint e7cf9fbdc8734acb
Analysis status DONE
Considered CTI value 0
Text language
Published Dec. 21, 2024, 11:03 a.m.
Added to db Dec. 21, 2024, 1:04 p.m.
Last updated Dec. 21, 2024, 1:05 p.m.
Headline Alignment Faking in AI: Even LLM can lie !
Title Alignment Faking in AI: Even LLM can lie !
Detected Hints/Tags/Attributes 11/1/0
Source URLs
Redirection Url
Details Source https://medium.com/@stephane.vallois/alignment-faking-in-ai-even-llm-can-lie-85b1a71f69f3?source=rss------cybersecurity-5
URL Provider
Details Provider Source level domain
Details medium.com medium.com
RSS Feed
Details Id Enabled Feed title Url Added to db
Details 167 ✔ Cybersecurity on Medium https://medium.com/feed/tag/cybersecurity 2024-08-30 22:08