


AI Security Table: candid conversations about AI, software, and security with Chris Romeo, Izar Tarandach & Matt Coles. Formerly The Security Table.


A human insider planting backdoors goes to jail. What happens to an AI agent that does it? #AISecurityTable #AIAgents


The case for using more tokens comes from the guy selling the tokens. Izar sees a problem. #AISecurityTable #AICoding

Patch the code you understand, or regenerate the code you don't? Pick one. #AISecurityTable #AppSec securitytable.ai/stop-patchi…

I'm a nerd and I'm ok I vibe all night and I hack all day.
Izar threat-modeled a separate identity for his AI agent. The lesson: he doesn't have enough of a life to need one. #AISecurityTable #AIAgents

Izar threat-modeled a separate identity for his AI agent. The lesson: he doesn't have enough of a life to need one. #AISecurityTable #AIAgents

Cisco gives one engineer unlimited tokens to rewrite 98% of its code. Altman says stop patching. Who's telling you to rewrite everything? The guy selling the tokens. #AISecurityTable #AISecurity #AICoding securitytable.ai/stop-patchi…

"Make no mistakes" is not a pragma. LLMs are not compilers. Stop treating them like one. #AISecurityTable #AppSec #Shorts

Claude writes the code, the patch, and the proof. Does compounded mistrust ever equal trust? #AISecurityTable #AISecurity #Shorts

Regex was everything. Then ASTs. Now tokens. Are LLMs the real thing or the next oversold scanner? #AISecurityTable #AppSec #LLM securitytable.ai/you-don-t-t…

Altman: We can't just patch all the bugs. Izar: The team said "security debt" on top of that. We stood there anyway. #AISecurityTable #AppSec #Shorts

You don't trust AI. So why ship its code? Altman says we can't patch all the bugs. Claude is writing its own proofs. Who checks the checker? #AISecurityTable #AISecurity #AppSec youtube.com/watch?v=xs67gzLv…

Claude reviewed Scion and added "excessive validation." Anthropic steered it back. Izar: "I was Claude in that scenario." Paranoid or right? #AISecurityTable #Claude #AISecurity

Once infrastructure gets comfortable for agents, humans stop looking. Izar thinks that bites us eventually. Chris thinks it's only the beginning. #AISecurityTable #AISecurity #AgenticAI

Scion is infrastructure rebuilt for agents first, people second. When your tools are optimized for agents, who's still checking what the agents did? #AISecurityTable #AISecurity #AgenticAI securitytable.ai/anthropic-d…