alt Hacker NewsI pasted your prompt:
ffmpeg command to convert movie.mov into a reasonably sized mp4
ffmpeg -i movie.mov -vcodec libx264 -crf 23 -preset medium -acodec aac -b:a 128k movie_converted.mp4
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.Replies
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.
What you and many other seem to miss is that the LLM is not deterministic.
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.
AI probably hates him so it acts dumb.
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.