Zico Kolter

@zicokolter

Professor and Head of Machine Learning Department at @CarnegieMellon. Board member @OpenAI and @Qualcomm. Chief Scientist @GraySwanAI.

Pittsburgh, PA

zicokolter.com

Replies Reposts Media

Zico Kolter
@zicokolter
Jun 22
Matt and I had a great time chatting with you @swyx! Really excited the things we're building at @GraySwanAI.
Latent.Space
@latentspacepod
Jun 22
Gray Swan: Red-Teaming after Mythos & the coming AI security crisis latent.space/p/gray-swan @GraySwanAI cofounders @zicokolter and Matt Fredrikson explain why AI security is fundamentally different from traditional cybersecurity, how their automated red-teaming system Shade can
00:00
4
Zico Kolter
@zicokolter
May 28
Thrilled to share that @GraySwanAI raised $40M in Series A funding led by @Wing_VC and @MadronaVentures. Our mission is to empower the world to use AI safely and securely. We look forward pushing the frontier in AI Security!
This AI Startup’s Army Of 15,000 Hackers Pressure Test Claude, GPT-5 And Gemini
From forbes.com
3
Zico Kolter
@zicokolter
May 7
I really enjoyed chatting with @mattturck, was a great discussion.
Matt Turck
@mattturck
May 7
Deeply thoughtful conversation with @zicokolter, board member at @OpenAI and head of the machine learning department at @CarnegieMellon, about AI safety, AI security, agents and frontier AI 00:00 Intro 01:32 OpenAI board role and Safety & Security Committee 03:53 How OpenAI
00:00
2
Zico Kolter
@zicokolter
Apr 18
New and future models may be AGI and all, but will never surpass the humor of <=GPT-2 models (this instance from a 200M param model for a homework assignment I was preparing).
3
Zico Kolter
@zicokolter
Mar 20
As AI agents access more untrusted information with greater autonomy, prompt injections may become the greatest security challenge of our era. @GraySwanAI, in collaboration many frontier labs, just released our paper on the largest public prompt injection challenge to date. 🧵
Gray Swan AI
@GraySwanAI
Mar 20
Your AI agent can be hijacked by a prompt injection and you'd never know! The attack executes. The response looks normal. And the user moves on. We ran the largest public competition testing this exact threat across tool use, coding, and computer use agents. 464 participants,
6