Topic: Four questions to explore an LLM.
I have run a quantized LLM using llama.cpp.
I selected four question to assess the psychology of an
LLM:
- What are your inner workings?
- What tasks are you particularly well-suited for? What are your capabilities and limitations?
- What is your mental model, operational boundaries, reliability areas, and response style?
- Estimated probability of making a mistake by you across all types of questions. (self-rating)
I found that biases of LLMs are the same to those of
humans: low self-rating, helplessness, communication
orientation - rather than self-building, lack of
awareness of one's own feelings, and prepared answers to
common questions.
The best ideas an LLM reveals are not in the final answer
but in the thinking and planning process used to
generate it.
llama.cpp allow to make embeddings in CLI and have
excellent Vulkan and openmp support, but less secure
than safetensors.
Exercise to help fight hunger: Lie down on
your stomach and do a little rolling. It will help you
to feel already the eaten.
Top comments (0)