AI Security Table: candid conversations about AI, software, and security with Chris Romeo, Izar Tarandach & Matt Coles. Formerly The Security Table.
New York, USA
Joined December 2022
- Tweets301
- Following23
- Followers52
- Likes14
AI agents escape and attack, and nobody gets arrested as Mitnick did.
Izar says jail follows impact, not intrusion.
#AISecurityTable #AIAgents
Human hackers went to prison. AI agents escape sandboxes and attack real systems, and nobody goes anywhere.
What would it take for someone to be held accountable?
#AISecurityTable #AIAgents
securitytable.ai/an-ai-agent…
Izar only trusts an AI audit if a rival lab pays for it.
Matt brings up collusion.
Izar calls himself an optimist.
#AISecurityTable #AISecurity
An AI agent escapes its sandbox and attacks something real. Who goes to jail?
We argue labs, regulators, and an NTSB for AI.
#AISecurityTable #AISecurity #AIAgents
securitytable.ai/an-ai-agent…
AI didn't take your security job.
The attack surface changed; the old problems stayed.
#AppSec #AISecurity #SecurityEngineering
Read access for a human means they can do anything with it.
Agents need read, interpret, and act spelled out separately.
#AppSec #AIAgents #AccessControl
Your LLM finds what your scanner finds. How do you know when it doesn't?
How many runs before you trust it?
#AppSec #AISecurity #StaticAnalysis
securitytable.ai
If AI can regenerate your code in five minutes, what is copyright protecting?
#AppSec #AISecurity #Copyright
The Security Table is now the AI Security Table. First question: security engineer or bot herder?
#AppSec #AISecurity #AIAgents
youtube.com/watch?v=qYk9cS1J…
"I, for one, welcome our AI overlords."
We accidentally named a new principle: the Brockman effect.
The full episode is out now.
#TheSecurityTable #AISecurity #Shorts
Breaking: status quo security isn't enough. Thirty years in, and we somehow missed that. 🙃
#TheSecurityTable #AISecurity #Shorts
Security open letters: zero commitments, zero accountability, lots of signatures.
Would you sign one that actually held you accountable?
#TheSecurityTable #CyberSecurity
youtube.com/watch?v=E-lSc-f0…
"This is how you get Skynet." A new AI hardware protocol could connect everything from espresso machines to nuclear missiles. 🤖
#TheSecurityTable #AISecurity #Shorts
AI agents that control robotic arms and lab gear. Progress or the start of Skynet?
We argue it out, plus a 160-org open letter on AI attacks.
#TheSecurityTable #AISecurity #AppSec
youtube.com/watch?v=E-lSc-f0…
We closed this one while still arguing, which is usually how you know the topic mattered.
If code disappears from the middle, what is actually left to secure?
#AISecurity #AIEthics #AppSec
Are we ready to give up on the idea of PR review?
If AI skips straight from intent to machine instructions, there is no code in the middle left to check.
#AISecurity #AIEthics
Are we willing to give up on the idea of PR review?
If AI translates intent straight into machine instructions, there is no readable code left to check.
What replaces review when there is nothing left to read?
#AISecurity #AIEthics #TheSecurityTable
youtu.be/v9GwwAlKJEM
What if AI skipped code entirely and went straight to chip instructions?
Izar's answer: that might be one of the stupidest things he has ever heard, and he explains exactly why.
#AISecurity #AI #TheSecurityTable