Science & Technology

Anthropic researchers find a way to jailbreak AI | TechCrunch Minute

Researchers at Anthropic just found a new way to trick AI into giving you information it’s not supposed to. AI companies have attempted to keep chatbots like OpenAI’s ChatGPT or Google’s Gemini from sharing dangerous information with a varying degree of success. But Anthropic researchers found a new way around current AI guardrails: a new…

Published

2 months ago

on

Researchers at Anthropic just found a new way to trick AI into giving you information it’s not supposed to. AI companies have attempted to keep chatbots like OpenAI’s ChatGPT or Google’s Gemini from sharing dangerous information with a varying degree of success.

But Anthropic researchers found a new way around current AI guardrails: a new approach they’re calling “many-shot jailbreaking.” It works by asking a chatbot simple questions to trick it into giving you information it normally wouldn’t later the conversation. As with many things with AI, it’s unclear why it works — but what we do know is that something within the latest language learning models allows them to home in on what a user wants.

Subscribe for more on YouTube:

Follow TechCrunch on Instagram:
TikTok:
X:
Facebook:

Read more:

Related Topics:

2 Comments

  1. @BUY_YOUTUBE_VIEWS_d123

    April 4, 2024 at 4:13 pm

    How do you always make such good videos 🔥

    Reply

  2. @lancemarchetti8673

    April 6, 2024 at 1:48 am

    Very interesting. I hope this doesn’t encourage content security companies to release excessive Nightshade poisoning into LLMs.
    I personally don’t feel that’s the way forward just because of bad actors?

    Reply

Leave a Reply

Your email address will not be published. Required fields are marked *

Trending

Exit mobile version