| ▲ | noelwelsh 10 hours ago |
| Well, that was extremely boring. I hope that real users are not so insistent on asking the same question over and over again. |
|
| ▲ | golol 6 hours ago | parent [-] |
| I wonder if here is a bug. For me it also always repeats the initial question. |
| |
| ▲ | jszymborski 4 hours ago | parent [-] | | The original GPT models did this a lot iirc. | | |
| ▲ | daveguy 38 minutes ago | parent [-] | | Maybe the role reversal breaks most of the RLHF training. The training was definitely not done in the context of role reversal, so it could be out of distribution. If so, this is a glimpse of the intelligence of the LLM core without the RL/RAG/etc tape and glue layers. |
|
|
