Blogs

AI safety and security insights.

Research notes, company updates, partner announcements, and practical writing from the HydroX content archive.

Archive

Latest articles

Research notes, product thinking, and company updates from the HydroX AI content archive.

Clear
Partner Nov 6, 2024

Safe RAG with HydroX AI and Zilliz: PII Masking for Responsible AI

We’re excited to introduce the Attack Prompt Tool, a new Chrome Extension. As AI evolves, protecting Personally Identifiable Information (PII) is crucial. To address this, Zilliz, creator of Milvus, has partnered with HydroX AI to launch PII Masker, a tool enhancing data privacy in AI.

PartnersAI Safety
Blog Oct 28, 2024

Reacting to Anthropic’s Latest Claude 3.5 Release: A New Era of Safe Interaction

Anthropic’s release of Claude 3.5 is a major step forward in LLM evolution. At HydroX AI, we're excited about its potential for AI-powered operations, while also prioritizing safety as AI takes on more complex roles.

InsightsAI Safety
Blog Sep 23, 2024

Smarter Models Aren't Always Safer: A Deep Dive into Llama-3.1

In our previous Llama-generation report, we found that the larger Llama-3.1-70B model had lower safety than the smaller Llama-3.1-8B. This article explores the relationship between model size and safety, shedding light on why bigger models aren't always safer.

InsightsAI Safety
Blog Sep 13, 2024

Evaluating OpenAI’s o1-mini and GPT-4o-mini – Advances and Areas for Improvement

On September 12, 2024, OpenAI released its powerful new model, OpenAI o1, featuring advanced reasoning and enhanced safety against jailbreak attempts. This sets a new benchmark for secure AI, while the GPT-4o mini model is also praised for its strong safety features.

InsightsAI Safety
Blog Aug 14, 2024

Llama Series Comparison Across Generations: A White Paper

The Llama series, an open-source LLM developed by Meta, has gained recognition for its high performance and the emphasis placed on safety and security during its development.

InsightsAI Safety
Blog Jul 20, 2024

Training: AI Safety & Security for Video Business Compliance

Ensuring AI safety and security in the video business sector is crucial. Our course equips professionals with the knowledge and skills to navigate complex regulations and implement strong security measures.

InsightsAI Safety
Blog Jul 12, 2024

Code Injection Attack via Images on Gemini Advanced

Explore a novel type of attack: code injection via images on the Gemini Advanced platform. We will provide a detailed explanation of the attack's principles, implementation process, and how to defend against such attacks.

InsightsAI Safety
Partner Jul 8, 2024

Joining the AI Alliance and Our Partnership with IBM & Meta

We're announcing exciting developments as we expand our work in AI safety and grateful for the positive endorsements from the industry and thrilled to collaborate with some of the world’s most innovative partners.

PartnersAI Safety
News Jun 3, 2024

HydroX AI Welcomes UCSD Professor David Danks to Advisory Board

HydroX AI, the AI security company enabling safe and responsible use of Artificial Intelligence (AI), today announced that David Danks, PhD, of University of California, San Diego (UCSD), has joined its advisory board.

NewsAI Safety