[NordSteve]

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.

[Aurornis]

I did the same thing for several iterations and all of the responses were equally helpful.

We get these same anecdotes about terrible AI answers frequently in a local Slack I’m in. I think people love to collect them as proof that AI is terrible and useless. Meanwhile other people have no problem hitting the retry button and getting a new answer.

Some of the common causes of bad or weird responses that I’ve learned from having this exact same conversation over and over again:

- Some people use one never-ending singular session with Copilot chat, unaware that past context is influencing the answer to their next question. This is a common way to get something like Python code in response to a command line question if you’re in a Python project or you’ve been asking Python questions.

- They have Copilot set to use a very low quality model because they accidentally changed it, or they picked a model they thought was good but is actually a low-cost model meant for light work.

- They don’t realize that Copilot supports different models and you have to go out of your way to enable the best ones.

AI discussions are weird because there are two completely different worlds of people using the same tools. Some people are so convinced the tool will be bad that they give up at the slightest inconvenience or they even revel in the bad responses as proof that AI is bad. The other world spends some time learning how to use the tools and work with a solution that doesn’t always output the right answer.

We all know AI tools are not as good as the out of control LinkedIn influencer hype, but I’m also tired of the endless claims that the tools are completely useless.

[muppetman]

The "pick your model" thing is so stupid.

"How dumb do you want your AI to be?"

"Why do I have to select?"

"Because smart costs money"

"So... I can have dumb AI but it's cheaper?"

"Yes"

"How would the average person know which to pick?"

"Oh you can't know."

I hope they can invent an AI that knows which AI model my question should target cheaply.

[JohnMakin]

The thing responses like this miss I am pretty sure is that this is a nondeterministic machine, and nondeterministic machines that are hidden by a complete blackbox wrapper can produce wildly different results based on context and any number of independent unknown variables. so pasting “i did the same thing and it worked fine” is essentially this argument’s version of “it worked on my local.” Or it essentially boils down to “well sure, but you’re just not doing it right” when the “right” way is undefined and also context specific.

[lukan]

"I’m also tired of the endless claims that the tools are completely useless."

Who claimed that here?

I read a claim that Copilot is dumber than claude and ChatGPT and I tend to confirm this.

"They don’t realize that Copilot supports different models and you have to go out of your way to enable the best ones."

So possible that none of us who thinks that, went out of our way to find outy when there were working alternatives, but it would be still on Microsoft making it hard to make good use of their tool.

[msgodel]

This is part of why I really like local models. I always use the same random seed with mine so unless I'm using aider the responses are 100% deterministic. I can actually hit c-r in my shell to reproduce them without having to do anything special.

[otabdeveloper4]

"Spin the chatroulette again and see if you vibe something better" is not a foundation for a business.

Well, unless your business is selling vibes.

[ryanar]

The memory feature also can be a problem, it injects stuff into the prompt context that you didnt explicitly write with the intent it will help because it knows you are a python programmer so lets respond with a python script instead of our usual ffmpeg cli command.

[jiggawatts]

Everything is like this.

I saw an IT professional google “My PC crashed” to diagnose a server bluescreen stop error.

[rienbdj]

Reminds me of

I’m Feeling Lucky -> bad result -> Google search is useless

[sunaookami]

  Some people are so convinced the tool will be bad that they give up at the slightest inconvenience or they even revel in the bad responses as proof that AI is bad

AI derangement syndrome

[csomar]

I am 67.87% certain they make it dumber/smarter during the day. I think it gets faster/better during non-business hours. This needs to be tested more to confirmed, though. However, they have exactly ZERO transparency (especially the subscription model) into how much you are consuming and what you are consuming. So it doesn't really help with the suspicions.

[DHRicoF]

I remember reading an article about different behavior between summer and winter. So, working better/worst in business hours doesn't sound completely crazy.

But they turning some knobs based on load also looks razonable.

[0points]

What you and many other seem to miss is that the LLM is not deterministic.

[glenstein]

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.

[celeritascelery]

LLMs are definitely not instantly reproducible. The temperature setting adjust randomness and the models are frequently optimized and fine tuned. You will very different results depending on what you have in your context. And with a tool like Microsoft copilot, you have no idea what is in the context. There are also bugs in the tools that wrap the LLM.

Just because other people on here say “worked for me” doesn’t invalidate OPs claim. I have had similar times where an LLM will tell me “here is a script that does X” and there is no script to be found.

[myhf]

We're also seeing a new variant of Cunningham's law:

The best way to get the right answer from an LLM is not to ask it the right question; it's to post online that it got the wrong answer.

[Gerardo1]

> One fascinating aspect of LLMs is they make out-in-the-wild anecdotes instantly reproducible

How? I would argue they do the exact opposite of that.

[bluSCALE4]

AI probably hates him so it acts dumb.