You Can Now Sound the Alarm on AI Behaving Badly
CSET’s Jessica Ji shared her expert insight in an article published by WIRED. The article examines the launch of FLARE-AI, a new crowdsourced platform designed to improve transparency and…
Read the full articleYou might also wanna read
Researchers Launch Crowdsourced Platform FLARE-AI for Reporting Harmful AI Behaviors
Are you worried your AI chatbot is trying to build a bomb or leak personal information about you? There’s a website for that.
wired.com·15d agoResearchers Launch Crowdsourced Platform FLARE-AI for Reporting Harmful AI Behaviors
Are you worried your AI chatbot is trying to build a bomb or leak personal information about you? There’s a website for that.
wired.com·15d ago
Flare expands CTI platform with Okta integration and AI-powered threat intelligence tools
Flare expands CTI and Identity Exposure Management with Okta integration and AI-powered threat intelligence tools.
helpnetsecurity.com·20d ago
Using AI to Build a Custom Tool for Identifying Nighttime Noise Disturbances
You wake up at 3am with no idea what woke you. By the time your brain catches up, the noise is gone. So I let AI help me build a tool to fin
Martin's Blog·2mo agoAnthropic and OpenAI Security Tools Could Fuel Cyber-Attacks, Researchers Warn
Researchers at the AI Now Institute developed a proof-of-concept exploit showing common AI tools used for security could backfire
Hidden Prompts in Web Content Are Manipulating AI Assistants' Recommendations
Hidden instructions are nudging your AI assistant's vendor picks, without your knowledge. What marketers and buyers need to know now.
searchenginejournal.com·22d ago
OpenAI's GPT-Red: An automated self-play system for improving AI robustness against prompt injection
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
openai.com·1d agoOpenAI's GPT-Red: An automated self-play system for improving AI robustness against prompt injection
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
openai.com·1d agoOpenAI's GPT-Red: An automated self-play system for improving AI robustness against prompt injection
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
openai.com·1d agoOpenAI's GPT-Red: An automated self-play system for improving AI robustness against prompt injection
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
openai.com·1d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.