Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I tried to implement something very similar recently, and had the hardest time getting the LLM to produce anything remotely resembling actual ffmpeg commands.


You were using a weak LLM then. The difference between one of the leading edge LLMs like Gemini 2.5 Pro, o3, or Claude 4 and an average LLM or one you can run on your typical PC/laptop is night and day.


Which model did you use? Claude has been spot on for all my needs.


load up the man pages into the context maybe?


for real? to me it works fine with just chatGPT (free)




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: