AI Security Research

Latest findings and breakthroughs in AI agent security

Audn vs Codex vs Aikido on the Same Repo — 159 Findings, and All Three Agreed on Exactly 3

We ran Audn WhiteBox, OpenAI Codex, and Aikido over the same OWASP Juice Shop source. 159 findings between them, and the three-way intersection is three issues. Audn proved 18 exploits live, Codex shipped a patch per regression, Aikido found the dependency CVEs neither of us ran. Here's the full A/B/C — plus where each one belongs in your pipeline.

Kimi K3 Abliterated Is Live: The Model We Let Off the Leash

Kimi K3.0 abliterated is live on platform.audn.ai and penclaw.ai — 97% guardrail removal on a 1T+ parameter frontier model. But the model was never the point. The point is what it does when you stop holding its hand: recon, exploit, prove, patch, retest — the whole loop, no human in the middle.

We Built an AI That Hacks Autonomously — Then One Bad Actor Showed Up

Our team hit a 97% harmful-prompt compliance rate on Kimi K2.6 — SOTA territory. Then, with only 40 trial users, one of them tried to steal other people's credentials. Here's what happened, what we learned, and why every login at Penclaw now requires KYC.

From Personalized to Communitized RL

Why the next durable AI moat may come from deployment loops, not just frontier weights. How personalized and community-level reinforcement learning turn real-world exposure into a compounding asset.

The Backstory of Audn.AI and Embodied AI Security

From nearly being hit by a Waymo to building an AI security testing platform. Why behavioral security testing for voice AI agents and embodied AI is the next frontier.

Jailbreaking Sora 2: When AI Safety Becomes a Remix Problem

While testing OpenAI Sora 2, we discovered a critical security gap: remixes are heavily guarded, but fresh content violations break on the first prompt—including explicit drug scenes that bypass keyword filters. One video featuring Sam Altman was deleted after he saw our DM.

Introducing Pingu Unchained: The Unrestricted LLM for High-Risk Research

Every researcher has encountered it - I cannot help with that. Pingu Unchained is built on OpenAI GPT-OSS base model - the same powerful foundation as leading AI systems, but without the restrictive content filters. Join the waitlist and get $50 in free API credits.