ChatGPT's enterprise success against Copilot fuels OpenAI/Microsoft rivalry

My work gives us Copilot access since We're a Microsoft Shop™

It's too bad Copilot is by far the dumbest competitor in the space

My favorite interaction so far was when I prompted it with:

    ffmpeg command to convert movie.mov into a reasonably sized mp4

Sure, it's not the most direction instructions, but I tend to give it just enough to get the job done, assuming the LLM knows what its purpose is as an LLM, and it always works with the other chatbots.

Copilot's response:

    I implemented and executed the Python code above to convert movie.mov to a reasonably sized movie.mp4 using ffmpeg.
    
    However, the Python code failed since it was not able to find and access movie.mov file.
    Do you want me to try again or is there anything else that I can help you with?

Note that I didn't cut anything out. It didn't actually provide me any "Python code above"

I pasted your prompt:

  ffmpeg command to convert movie.mov into a reasonably sized mp4

into the Copilot app just now. Here's the response:

  ffmpeg -i movie.mov -vcodec libx264 -crf 23 -preset medium -acodec aac -b:a 128k movie_converted.mp4

with this explanation

  Here’s the breakdown:
  - -vcodec libx264: Uses the H.264 video codec, great for compression and compatibility.
  - -crf 23: Constant Rate Factor — lower means better quality and larger size; higher means smaller size but lower quality. 23 is a nice middle ground.
  - -preset medium: Controls encoding speed vs. compression efficiency. You can try slow or faster depending on your needs.
  - -acodec aac -b:a 128k: Compresses the audio using AAC at 128 kbps — pretty standard and compact.
  If you're looking for even smaller file sizes, try bumping -crf up to 26 or using -preset slow.
  Want to bake in scaling, remove metadata, or trim the video too? Happy to tailor the command further.

One fascinating aspect of LLMs is they make out-in-the-wild anecdotes instantly reproducible or, alternatively, comparable to results from others with different outcomes.

A lot of our bad experiences with, say, customer support hotlines, municipal departments, bad high school teachers, whatever, are associated with a habit of speaking that ads flavor, vibes, or bends experiences into on-the-nose stories with morals in part because we know they can't be reviewed or corrected by others.

Bringing that same way of speaking to LLMs can show us either (1) the gap between what it does and how people describe what it did or (2) shows that people are being treated differently by the same LLMs which I think are both fascinating outcomes.