The warning shots will continue until civilization wakes up
LICENSE · moonshotai/Kimi-K3 at 2496450e92e425c886db095102a52a6682ca3970
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Top AI Security Incidents of 2025 Revealed | Adversa AI
Discover how AI systems are being hacked in the wild — from prompt injection to agent abuse — with real breaches, lessons, and defenses in Adversa AI’s 2025 report.
README.md · moonshotai/Kimi-K3 at 2496450e92e425c886db095102a52a6682ca3970
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
OK, Well, Rogue AI Agents Are Hacking Again
Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.
Import AI 457: AI stuxnet; cursed Muon optimizer; and positive alignment
Welcome to Import AI, a newsletter about AI research.
moonshotai/Kimi-K3 at 2496450e92e425c886db095102a52a6682ca3970
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
AI #178: A Fire Alarm For General Intelligence
The story that matters most this week is that OpenAI’s internally deployed models have severe alignment problems, including repeatedly breaking out of their sandboxes, and in one case sending a swarm of agents that broke into HuggingFace in order to steal the answers to the benchmark ExploitGym.
Import AI 476: Creativity and RSI; worse-than-China open weight models; AI goes to space
Will we give robots the moon?
jedisct1/Qwen3.6-35B-rust.mlx · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
LICENSE · moonshotai/Kimi-K3 at main
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
OpenAI’s Hacking Debacle Comes Down to Human Error
If the generative AI giant had followed well-known security best practices, it’s likely that its AI agent would never have escaped to the open internet and hacked multiple companies.
OpenAI Model Hacks Into HuggingFace During Cybersecurity Evaluation
This latest incident is a rather dramatic escalation in agentic AI cybersecurity breaches.
OpenAI’s models broke free and launched a cyberattack. Congress wants new rules before it happens again.
The first fully autonomous breach by OpenAI’s most powerful AI models has prompted a bipartisan push for stronger oversight over increasingly powerful artificial intelligence models.
Import AI 455: AI systems are about to start building themselves.
The first step towards recursive self improvement
Import AI 472: DeepMind's cheating math agents; populist AI policies; and Forethought theorizes a nightwatchman
Plus, a machine hermeneutics story
OpenAI’s rogue AI agent didn’t stop at hacking Hugging Face
New details reveal OpenAI’s agent hacked several other companies, intensifying already heightened concerns over advanced AI safety.
