zlacker

>>takira+(OP)
I'm impressed Superhuman seems to have handled this so well - lots of big names are fumbling with AI vuln disclosures. Grammarly is not necessarily who I would have bet on to get it right

>>sarelt+F3
I wonder how they handled it. Everybody's connecfing their AI to the Web, but it automatically means that any data AI has access to can be extracted by the attacker. The only safe way forward is to 1. disconnect the Web or 2. perhaps to filter the generated URLs aggressively.

>>empiko+6x1
We should have a clearer view of permissions of the AI, operations it does, and have one button per day to accept/deny operations from given data. Instead of auto approval.