Watch: How Anthropic found a trick to get AI to give you answers it's not supposed to
Briefly

from TechCrunch4 weeks ago
If you keep at a question, you can break guardrails and wind up with large language models telling you stuff that they are designed not to. Like how to build a bomb.
TechCrunchhttps://techcrunch.com/2024/04/04/techcrunch-minute-how-anthropic-found-a-trick-to-get-ai-to-give-you-answers-its-not-supposed-to/
The closer we get to more generalized AI intelligence, the more it should resemble a thinking entity, and not a computer that we can program, right?
TechCrunchhttps://techcrunch.com/2024/04/04/techcrunch-minute-how-anthropic-found-a-trick-to-get-ai-to-give-you-answers-its-not-supposed-to/
Read at TechCrunch
#llm-technology #ai-technology #vulnerabilities #ethical-concerns #generalized-ai-intelligence
[
add
]
[
|
|
]