{"channel":"llm","content":"To write a few paragraphs on a topic, there is (roughly) a four-step process:\r\n\r\n# Choose a topic\r\n# Create an argument\r\n# Choose the tone and style\r\n# Write the words\r\n\r\nThe *machine* is, in many situations, better than I am at the task of << writing >> the words. ( it still struggles with a few tones) It is always about 20 times faster than me.\r\n\r\nHowever, it struggles with the first three tasks.\r\n\r\n# The \"agent\" framework isn't focused on self-willed agents. This is (probably) a good thing. But \"fiduciary\" agents aren't happening either yet. These solve some of the problem related to motivation.\r\n# The *machine* prefers to create a good-sounding argument to a logically-sound one. ( of course, many humans do the same thing).\r\n# The *machine* defaults to a tone that has been over-used to the point of annoyance. It is obsequious and aggressively cheerful. In the context of \"a chat-bot for people unfamiliar with the technology\", this is a defensible choice. But, most of the time, you need your own tone. ( It has been long enough that the training data allows \"write a tone prompt for this query\" kind-of works.)","created_at":"2025-04-22T18:09:16.429218","id":354,"llm_annotations":{},"parent_id":null,"processed_content":"

To write a few paragraphs on a topic, there is (roughly) a four-step process:\r

\n
    \n
  • Choose a topic\r
    • \n
  • Create an argument\r
    • \n
  • Choose the tone and style\r
    • \n
  • Write the words\r
    • \n
\n

The machine is, in many situations, better than I am at the task of writing the words. \n \ud83d\udca1\n ( it still struggles with a few tones)\n It is always about 20 times faster than me.\r

\n

However, it struggles with the first three tasks.\r

\n
    \n
  • The \"agent\" framework isn't focused on self-willed agents. This is (probably) a good thing. But \"fiduciary\" agents aren't happening either yet. These solve some of the problem related to motivation.\r
    • \n
  • The machine prefers to create a good-sounding argument to a logically-sound one. \n \ud83d\udd25\n ( of course, many humans do the same thing)\n .\r
    • \n
  • The machine defaults to a tone that has been over-used to the point of annoyance. It is obsequious and aggressively cheerful. In the context of \"a chat-bot for people unfamiliar with the technology\", this is a defensible choice. But, most of the time, you need your own tone. \n \ud83d\udca1\n ( It has been long enough that the training data allows \"write a tone prompt for this query\" kind-of works.)\n
    • \n
","quotes":[],"subject":"writing with the LLM"}