Stealth LLM: im-a-good-gpt2-chatbot

Pure performance testing of two new stealth LLMs im-a-good-gpt2-chatbot and im-also-a-good-gpt2-chatbot, released on LMsys.org for a limited period of time, in a unique marketing stunt of an unknown corporation. Live session. Just live tests, no speculation.

Tested on a unique interdisciplinary prompt and then basically the test procedure by Stanford Univ. This is now my fifth video with this test suite for causal reasoning /logical reasoning.


#airesearch

chatbot good gpt2 gpt2-chatbot llm llms lmsys marketing performance prompt session speculation stanford stealth test testing tests unique video