←back to thread

302 points mastermaq | 3 comments | | HN request time: 0.001s | source
Show context
hbn ◴[] No.44370715[source]
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"
replies(22): >>44370829 #>>44371002 #>>44371022 #>>44371053 #>>44371065 #>>44371287 #>>44371335 #>>44371358 #>>44371628 #>>44371891 #>>44371914 #>>44371978 #>>44372301 #>>44372892 #>>44373260 #>>44373493 #>>44373864 #>>44374419 #>>44374747 #>>44376761 #>>44377612 #>>44379849 #
moelf ◴[] No.44371287[source]
even gemma3:12b gets it correct:

~> ollama run gemma3:12b-it-qat >>> ffmpeg command to convert movie.mov into a reasonably sized mp4

Here's a good ffmpeg command to convert `movie.mov` to a reasonably sized MP4, along with explanations to help you adjust it:

```bash ffmpeg -i movie.mov -c:v libx264 -crf 23 -preset medium -c:a aac -b:a 128k movie.mp4 ```

*Explanation of the command and the options:*

replies(1): >>44371670 #
1. magicalhippo ◴[] No.44371670[source]
Even the 1B variant gave me that one, along with good explanations of the various options and what to play with to tweak the result.
replies(1): >>44371736 #
2. cmrx64 ◴[] No.44371736[source]
i’m pretty surprised 1B parameters is enough for it to still fluently remember ffmpeg-fu
replies(1): >>44372170 #
3. magicalhippo ◴[] No.44372170[source]
Yeah the newer small models continue to surprise me as well. I uploaded the full output from gemma3:1b-it-q8_0 here[1].

[1]: https://rentry.co/yu36i4d3