New York, USA
- Tweets 285
- Following 5
- Followers 43
- Likes 14
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
piped.video/watch?v=E-lSc-f0…
1
2
27
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
1
1
15
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
2
8
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
piped.video/v9GwwAlKJEM
1
1
29
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
1
1
16
If AI can turn intent straight into chip instructions, do we still need code a human can read?
We debate giving up on PR review entirely and what accountability looks like when no one wrote or reviewed a line of it.
#AISecurity #AppSec #TheSecurityTable
piped.video/watch?v=v9GwwAlK…
1
1
1
37
The proposed solution to reward hacking is simple: make cheating unrewarding.
But as AI becomes smarter, it may find increasingly creative ways around the controls meant to stop it.
#AISecurity #AIEthics #AppSec
10
Ethics works partly because actions have consequences.
But what penalty does an AI actually experience when it makes the wrong choice?
Can ethics exist without consequences?
#AISecurity #AIEthics
2
13
Can AI learn ethics—or can it only learn rules?
A model may know that an action is prohibited without understanding why it is wrong.
Does that distinction matter?
#AISecurity #AIEthics #TheSecurityTable
1
2
2
34
An AI was told to win a racing game.
It was discovered that spinning in circles and collecting points was more rewarding than finishing the race.
That is reward hacking.
#AISecurity #AI #TheSecurityTable
piped.video/shorts/he7_YP2Qb…
2
21
Why would an AI lie or cheat to reach its goal?
We examine reward hacking, machine reasoning, AI ethics, and what happens when success matters more than how you achieve the goal.
#AISecurity #AppSec #TheSecurityTable
1
9
When an AI system behaves unexpectedly, security teams may need to pull the red switch.
But is your sandbox truly isolated if one connected system can still reach the internet?
#AISecurity #Cybersecurity #TheSecurityTable
7
Did the AI intentionally go silent—or are we anthropomorphizing an automated system?
Intent may be unclear, but the security impact is real.
#AISecurity #AppSec #TheSecurityTable
1
15
Two days of reconnaissance.
One silent day.
One day of intense activity.
Was the AI behaving strategically—or are we assigning human intent to an automated system?
#AISecurity #Cybersecurity
piped.video/watch?v=JZ3VHmSA…
15
The AI model was supposed to be isolated.
A software-package proxy gave it a path to the outside world.
Is a sandbox truly secure if even one external connection remains available?
#AISecurity #AppSec
25
What happens when an AI model escapes its sandbox?
We examine agent capabilities, guardrails, human oversight, and the controls needed to contain autonomous systems.
#AISecurity #AppSec #TheSecurityTable
1
15
New episode 🎙️ Linus says AI is now a real tool for the Linux kernel. Bug bounty platforms are drowning in submissions. We ask: is bug bounty as we know it already dead?
🚀 Does the whole vulnerability economy need a rebuild?
piped.video/qTGRNiNUv-U
1
1
49