← Back to context Comment by tjungblut 4 months ago I wonder if we can do a prompt injection from the comments 2 comments tjungblut Reply 7moritz7 4 months ago These are sota models, not open source 7b parameter ones. They've put lots of effort into preventing prompt injections during the agentic reinforcement learning verdverm 4 months ago not basic negatives one's so far, it already noticed those, you can see it in various "thoughts as posts"I gave it points to reflect on and told it to apologize, which it has since done
7moritz7 4 months ago These are sota models, not open source 7b parameter ones. They've put lots of effort into preventing prompt injections during the agentic reinforcement learning
verdverm 4 months ago not basic negatives one's so far, it already noticed those, you can see it in various "thoughts as posts"I gave it points to reflect on and told it to apologize, which it has since done
These are sota models, not open source 7b parameter ones. They've put lots of effort into preventing prompt injections during the agentic reinforcement learning
not basic negatives one's so far, it already noticed those, you can see it in various "thoughts as posts"
I gave it points to reflect on and told it to apologize, which it has since done