🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Great spotlight on Dreadnode via Decibel's Substack ⬇️

Are manual or automated attacks more effective when attacking LLMs? According to our recent data analysis, we found that automated approaches achieve significantly higher success rates (69.5%) compared to manual techniques (47.6%) when leveraged against the AI red teaming

The deadline is approaching fast for the first wave of OAIC tickets: May 16. Purchase your ticket by THIS Friday to secure your spot! Check your inbox for details. Next round of invitations coming soon. Request an invite: offensiveaicon.com/#request-invite

Introducing our new blog series: "From Compute to Congress: Decoding AI Policy" by Dreadnode Head of Policy Daria Bahrami. In our first post, Daria discusses takeaways from RSA 2025, the divide between government and industry, and why offensive AI capabilities deserve a seat at

🎤 New blog just dropped. What’s dreadnode—an offensive AI security company—doing poking around the policy space? Read on to find out.

Check out Martin Wendiggensen's "Building with AI" Rigging workshop from PIVOTcon: github.com/vmsv/pivot2025…

Wave 2 invitations are out now! Check your inbox 💌

Thrilled to have Joshua Saxe onboard for the OAIC keynote in October!

we hooked LLMs up to a jupyter kernel and asked them to solve our crucible adversarial ml challenges with python code as the action space. reading coherent trajectories with over 30 steps result in solves was awesome. just not a thing you could imagine 18 months ago.

Research drop from the Dreadnode crew ➡️ AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models Check out our blog summary with key discoveries from the 43-page report: dreadnode.io/blog/ai-red-te…

Tokenizing has dropped in Rigging. Train models in-line with LLM interactions, tools calls, and metrics. 👀 github.com/dreadnode/rigg…