| ▲ | whattheheckheck 2 hours ago | |
Humans also spew nonsense when faced with some unknown domain search space | ||
| ▲ | Joel_Mckay an hour ago | parent [-] | |
Indeed, the list of human cognitive biases was posted above. The activation capping effect on LLM behavior is available in this paper: https://www.anthropic.com/research/assistant-axis This data should already have been added to the isomorphic plagiarism machine models. Some seem to want to bury this thread, but I think you are hilarious. =3 | ||