At this point I'm so used to evil defaults, reverse psychology could work. Make the "deny all" button bright blue and the "gimme ads and viruses" button pale gray, and you might just catch me.
I think rozab has it right. What executes exfiltration request is the user's browser when rendering the output of the LLM. It's fine to have an LLM ingest whatever, including both my secrets and data I don't control, as…
Besides complexity, a price you pay with multi-armed bandits is that you learn less about the non-optimal options (because as your confidence grows that an option is not the best, you run fewer samples through it). It…
At this point I'm so used to evil defaults, reverse psychology could work. Make the "deny all" button bright blue and the "gimme ads and viruses" button pale gray, and you might just catch me.
I think rozab has it right. What executes exfiltration request is the user's browser when rendering the output of the LLM. It's fine to have an LLM ingest whatever, including both my secrets and data I don't control, as…
Besides complexity, a price you pay with multi-armed bandits is that you learn less about the non-optimal options (because as your confidence grows that an option is not the best, you run fewer samples through it). It…