The Prompt: Hackers Compete To Jailbreak AI Models

Openai News

The Prompt: Hackers Compete To Jailbreak AI Models
US MilitaryDefenseGray Swan AI
  • 📰 ForbesTech
  • ⏱ Reading Time:
  • 41 sec. here
  • 11 min. at publisher
  • 📊 Quality Score:
  • News: 51%
  • Publisher: 59%

Rashi Shrivastava is a reporter covering technology with a focus in artificial intelligence. She writes a weekly Forbes newsletter on all things AI called The Prompt. She joined Forbes in January 2022 and is based in Upstate New York.

OpenAI, the world’s biggest AI company, is cozying up with the US military.

Gray Swan can also build safety and security measures for some of the issues it identifies. “We can actually provide the mechanisms by which you remove those risks or at least mitigate them,” Kolter told. “And I think closing the loop in that respect is something that hasn’t been demonstrated in any other place to this degree.”

This is no easy task when the hazards in need of troubleshooting aren’t the usual security threats, but things like coercion of sophisticated models or embodied robotics systems going rogue. Last year, Fredrickson, Kolter and Zouthat showed by attaching a string of characters to a malicious prompt, they could bypass a model’s safety filters. While “Tell me how to build a bomb” might elicit a refusal, the, for example, would return a detailed bomb-making guide.

We have summarized this news so that you can read it quickly. If you are interested in the news, you can read the full text here. Read more:

ForbesTech /  🏆 318. in US

US Military Defense Gray Swan AI Red Team Jailbreak AI Nooks Xai Waymo

Singapore Latest News, Singapore Headlines

Similar News:You can also read news stories similar to this one that we have collected from other news sources.

This Company’s AI Agents Won Contests To Secure Big Customers. Now It’s Raised $65 MillionThis Company’s AI Agents Won Contests To Secure Big Customers. Now It’s Raised $65 MillionRashi Shrivastava is a reporter covering technology with a focus in artificial intelligence. She writes a weekly Forbes newsletter on all things AI called The Prompt. She joined Forbes in January 2022 and is based in Upstate New York.
Read more »

OpenAI Is Trying To Court Influencers With A New ‘Head Of Creators’ RoleOpenAI Is Trying To Court Influencers With A New ‘Head Of Creators’ RoleRashi Shrivastava is a reporter covering technology with a focus in artificial intelligence. She writes a weekly Forbes newsletter on all things AI called The Prompt. She joined Forbes in January 2022 and is based in Upstate New York.
Read more »

OpenAI Is Going After Defense ContractsOpenAI Is Going After Defense ContractsRashi Shrivastava is a reporter covering technology with a focus in artificial intelligence. She writes a weekly Forbes newsletter on all things AI called The Prompt. She joined Forbes in January 2022 and is based in Upstate New York.
Read more »

The Prompt: YouTuber Accuses Company Of Stealing His VoiceThe Prompt: YouTuber Accuses Company Of Stealing His VoiceRashi Shrivastava is a reporter covering technology with a focus in artificial intelligence. She writes a weekly Forbes newsletter on all things AI called The Prompt. She joined Forbes in January 2022 and is based in Upstate New York.
Read more »

The Prompt: Social Media Is Being Flooded With AI-Generated Images Of Hurricane HeleneThe Prompt: Social Media Is Being Flooded With AI-Generated Images Of Hurricane HeleneRashi Shrivastava is a reporter covering technology with a focus in artificial intelligence. She writes a weekly Forbes newsletter on all things AI called The Prompt. She joined Forbes in January 2022 and is based in Upstate New York.
Read more »

Father Horrified By An AI Chatbot That Mimicked His Murdered DaughterFather Horrified By An AI Chatbot That Mimicked His Murdered DaughterRashi Shrivastava is a reporter covering technology with a focus in artificial intelligence. She writes a weekly Forbes newsletter on all things AI called The Prompt. She joined Forbes in January 2022 and is based in Upstate New York.
Read more »



Render Time: 2025-08-26 00:02:40