ffmpeg-english
Dev tools
command line helper
SHOW HN2024
How HN took it
4 positive, 22 neutral or asking, 1 mixed, 28 critical, out of 55 comments about the project. Thread score -0.39.
Privacy: 0 for, 14 againstIdea: 3 for, 9 againstExecution: 1 for, 4 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fun idea and useful for quick ffmpeg tasks
From 2 comments
Terrible idea, I love it This is good use case for a well-trained LLM, rather than the broad scope of chatGPT
AzzyHN on HNI needed to speed up a video by dropping 9 out of every 10 frames yesterday. It took all of 30 seconds to type my request into GPT and paste the result, and I could inspect it…
hallway_monitor on HN
Objections
Executing LLM output without review is unsafe (shell injection, malicious commands)
From 4 comments
It's not a good use case for anything. Never ask a remote endpoint that's not owned by you and not run by you, what commands you should run on your system. Certainly don't…
amiga386 on HNGetting a suggested command from a chat bot is not a terrible idea. Directly executing commands given by a chat bot on your machine it without inspecting it first is pure madness.
tirpen on HNHere's a hypothetical but very real scenario: someone discovers a vulnerability in openAI's API (vulnerabilities are everywhere these days), you prompt it to do something for you…
axegon_ on HN…by sending your request to the ChatGPT API and then executing the result. What could possibly go wrong?
LeoPanthera on HN
Sending commands to a remote API is a privacy and trust risk
From 2 comments
It's not a good use case for anything. Never ask a remote endpoint that's not owned by you and not run by you, what commands you should run on your system. Certainly don't…
amiga386 on HN> Same goes for output from an LLM This is the crux of our disagreement. It does not go the same. You have no idea what the LLM is going to write, neither does the LLM, nor the…
amiga386 on HN
Requests
Use a local LLM instead of a remote API
From 1 comment
I do envision training a local LLM which would mostly resolve this concern, but at the moment the vast majority of people don't have a good enough GPU in their system to run an…
dheera on HN
Use subprocess with argument arrays rather than shell execution
From 2 comments
If you want this to be a little safer, instead of just those guardrails to prevent semicolons and such, you can split the command into an array of arguments, and use…
bonyt on HNPlease, do not use subprocess.Popen. Use something like plumbum, way safer and more robust.
zekrioca on HN
Questions
Why temperature 0.5 rather than 0?
From 2 comments
> temperature=0.5 Why not 0? I’m not a prompt engineer so I never worked with the API, but I thought the “temperature” was a little knob they added for variety in responses. Is…
fmbb on HNGood question! I used 0.5 out of habit, but I do need to do some more experimenting with this parameter. But yes, intuitively it should probably be low. I'll do some experiments…
dheera on HN
Alternatives named
GitHub Copilot CLI (??)
From 1 comment
I recommend `??` from GitHub Copilot. It's basically this, but for any command, not just ffmpeg. I use it all the time. And it asks for confirmation to execute the command :)…
H8crilA on HN
Open Interpreter
From 1 comment
http://openinterpreter.com will just run commands for you
fragmede on HN
llm-cmd
From 1 comment
This is what llm cmd does for any command, and it also offers a chance to edit it before running https://github.com/simonw/llm-cmd
imjonse on HN
Warp and Wave Terminal
From 1 comment
If you used any "new" terminal - like Warp [1] (which requires you to login to use wtf) or Wave Terminal[2] (open source and bring your own AI is supported) - you'll be very…
orliesaurus on HN