zlacker

[return to "Simulating History with ChatGPT"]
1. benbre+jl[view] [source] 2023-09-12 14:04:41
>>arbesm+(OP)
Author of the post here - happy to discuss and get feedback from HN readers. The examples I gave here are all using GPT-3.5 but Claude now seems to work at least as well using the same prompts.
◧◩
2. course+BC1[view] [source] 2023-09-12 19:16:10
>>benbre+jl
Really interesting post, I've been thinking a lot about similar uses LLMs to create immersive learning experiences.

I had some initial successes getting ChatGPT (3.5 and then 4) to roleplay interesting and dynamic characters. Within the first few months of release results degraded significantly - characters avoid confrontation, apologize at the drop of a hat, and are averse to any action or statement that doesn't 'help' the user. Makes it difficult to, say, have a passionate argument with Napoleon which pits his youthful revolutionary ideals against his rise to absolute power, when the 'great man' folds the moment he doesn't receive positive feedback.

I'm very interested in seeing these experiments in unrestricted models of similar power, when they become available.

[go to top]