Blog
Mar 11, 2025
New Research: Exploring the Impact of Output Length on LLM Safety
We’re excited to announce that HydroX AI is sponsoring and collaborating on new AI safety research. Our latest paper explores a key yet overlooked factor in LLMs: how output length affects model safety and reasoning.
InsightsAI Safety
Blog
Mar 4, 2025
Unlocking the Future of Cybersecurity with Roland Cloutier
In Episode 3 of Season 1 of the Attention Needed podcast, we chat with Roland Cloutier, a cybersecurity leader and former Global Chief Security Officer at TikTok.
PodcastsAI Safety
Blog
Feb 17, 2025
How to Interpret AI Safety in the Context of Culture, Ethics, and Regulation
See the 2nd Episode of Season 1 of the Attention Needed podcast, where we explore the intersection of responsible AI and governance with Dr. Rumman Chowdhury, CEO of Humane Intelligence.
PodcastsAI Safety
Blog
Feb 4, 2025
Introducing Attention Needed: A Podcast on AI and Safety
We’re excited to introduce The AI Alliance, a new podcast exploring AI advancements, challenges, and the importance of safety and security. Hosted by Victor Bian, our COO, it features conversations with top experts shaping AI's future.
PodcastsAI Safety
Blog
Jan 29, 2025
DeepSeek-R1-Distill Models: Does Efficiency & Reasoning Come at the Expense of Security?
DeepSeek, a Chinese AI company, has recently gained attention in the AI community. Known for its innovation, it has developed models that rival top systems — offering similar performance with lower cost and resource use.
InsightsAI Safety
Blog
Jan 8, 2025
The Safety Trade-offs of Advanced AI: Insights from Llama-3.3 and Tulu-3
Alongside major closed-source model announcements in late 2024, the open-source community also saw key releases. In this brief post, we explore Llama-3.3 and Tulu-3, evaluating their performance in terms of AI safety and security.
InsightsAI Safety
Blog
Dec 6, 2024
Uncovering AI Weaknesses: How Simple Prompts Threaten Agent Safety
AI agents powered by advanced LLMs like GPT-4 and Llama are revolutionizing human-machine interaction, but they come with risks. This blog explores how a simple adversarial strategy can reveal vulnerabilities and leading to dangerous consequences.
InsightsAI Safety
Blog
Nov 20, 2024
AI Scriper -- How AI-Powered Scrapers Are Redefining Red Teaming
AI-powered scrapers are not just faster—they're fundamentally more resilient and adaptive than their traditional counterparts.
InsightsAI Safety
Blog
Nov 11, 2024
Introducing the Attack Prompt Tool: A Simple Extension for AI Security Research
We’re excited to introduce the Attack Prompt Tool, a Google Chrome Extension that simplifies adversarial prompt testing for AI safety research. Designed for AI researchers and security professionals, it helps assess the resilience of LLMs against adversarial techniques, especially jailbreak prompts.
ProductsAI Safety