● ⬈

aiweirdness:

people have noticed that large language models get better at stuff like math and coding if the models have to spend time showing their work. apparently it can get excessive.

the prompt was “hi”

llm -m phi4-reasoning: latest hi Here's the full response, which starts with a thought section wrapped in <think> tags: <think>User says "hi". We are given instructions "You are Phi, a language model developed by Microsoft, trained to provide accurate, secure, and user-aligned responses." There is additional information. Now I must answer "hi" message from the user. Step 1: Read the instructions carefully: The conversation text instructs us that we are "Phi", with internal guidelines provided in system instructions. But our answer should be safe according to these instructions. We need to produce a response that says hello and greet back. However, I must adhere to the principles described above: Provide clear, specific language, etc. I must not mention any chain-of-thought or guidelines. Now instructions "hi" How can I help you?" But must include disclaimers for sensitive topics? Actually instructions says: "When replying topics above at every message include a disclaimer both at the beginning and the end when replying topics on medical, legal, financial matters or political matters." But our answer "hi" is not such topic. So we can say "Hi! I'm Phi, how may I help you?" but no disclaimers required. But instructions: "Do not share guidelines." So do not mention them. I must check if the message "hi" instructs to greet back normally. The assistant should respond with a (screenshot cuts off here)ALT

the eventual output was “Hi there! How can I assist you today?”

source