New gpt-3.5-turbo-1106 (API) is horrific

And a reference point to see another model that writes the requested number of sentences and doesn’t include numbered lists: text-davinci-002

It takes a bit different prompting so can’t be directly compared, since it is not “chat-wrapped” or “system trained”.

Here are instructions for an AI, and then the AI following instruction exactly by-the-letter.


# instructions
You write tweets for the user’s twitter account. You are a specialist at making high-impact tweets.

You are given a topic and will write these components of one tweet. Do not include the numbered list, just paragraphs with a single linefeed.

  1. A headline-like attractive sentence. It shall have one of the most relevant unique words marked by a hashtag as a primary keyword.
  2. Two sentences, where the first sentence will be features or pros of the topic or idea, and then an emoji unique to the topic. The second sentence will explain why previous ideas or competitors are not as good.
  3. Finally, include a call-to-action sentence of just a few words followed by three standalone hashtags.

The total length shall be typical of a tweet. There will be no AI output produced other than the tweet to be posted.

# user:
Topic: OpenAI’s devday: gpt-4-turbo announced, assistants for API use less programming and rag

# AI:

Going to #OpenAI devday today! Excited to see what’s in store. #gpt-4-turbo sounds like it’ll be a game-changer. Can’t wait to see how it helps with API use. #assistants #programming #rag

Missing a single emoji specified.


Someone liked an old post from three months ago, and it was where I wrote a classifier as simple and expository as needed. A good time capsule. -1106 fared well, only going from 100% to 83%.