Pinned post

Q&A with Google DeepMind VP of Research Pushmeet Kohli on launching AlphaFold 2 five years ago, hallucinations, building an "AI co-scientist", and more (Sandro Iannaccone/Wired)

Sandro Iannaccone / Wired : Q&A with Google DeepMind VP of Research Pushmeet Kohli on launching AlphaFold 2 five years ago, hallucina...

2 April 2024

Anthropic researchers detail "many-shot jailbreaking", which can evade LLMs' safety guardrails by including a large number of faux dialogues in a single prompt (Devin Coldewey/TechCrunch)

Devin Coldewey / TechCrunch:
Anthropic researchers detail “many-shot jailbreaking”, which can evade LLMs' safety guardrails by including a large number of faux dialogues in a single prompt  —  How do you get an AI to answer a question it's not supposed to?  There are many such “jailbreak” techniques …

Posted from: this blog via Microsoft Power Automate.

Do your Amazon shopping through this link.

By on