Comment by saagarjha 6 hours ago AI labs currently have no solution for this problem and have you shoulder the risk for it. 3 comments saagarjha Reply keepamovin 5 hours ago Evidence? simonw 5 hours ago If they had a solution for this the would have told us about it.In the meantime security researchers are publishing proof of concept data exfiltration attacks all the time. I've been collecting those here: https://simonwillison.net/tags/exfiltration-attacks/ saagarjha 5 hours ago I worked on this for a company that got bought by one of the labs (for more than just agent sandboxes, mind you).
keepamovin 5 hours ago Evidence? simonw 5 hours ago If they had a solution for this the would have told us about it.In the meantime security researchers are publishing proof of concept data exfiltration attacks all the time. I've been collecting those here: https://simonwillison.net/tags/exfiltration-attacks/ saagarjha 5 hours ago I worked on this for a company that got bought by one of the labs (for more than just agent sandboxes, mind you).
simonw 5 hours ago If they had a solution for this the would have told us about it.In the meantime security researchers are publishing proof of concept data exfiltration attacks all the time. I've been collecting those here: https://simonwillison.net/tags/exfiltration-attacks/
saagarjha 5 hours ago I worked on this for a company that got bought by one of the labs (for more than just agent sandboxes, mind you).
Evidence?
If they had a solution for this the would have told us about it.
In the meantime security researchers are publishing proof of concept data exfiltration attacks all the time. I've been collecting those here: https://simonwillison.net/tags/exfiltration-attacks/
I worked on this for a company that got bought by one of the labs (for more than just agent sandboxes, mind you).