HackerTrans
TopNewTrendsCommentsPastAskShowJobs

malborodog

no profile record

comments

malborodog
·3 năm trước·discuss
I am going to ask gpt 4 to implement this for me so I can see what it looks like. Amazing.
malborodog
·3 năm trước·discuss
why not just have a tonne of html files on disk?? I'm confused at why this requires a sophisticated backend.
malborodog
·3 năm trước·discuss
(1) could you hash everyone's mp3 files so that if person a had the same songs as person b, you only need to store them once? (2) people obviously storing copyright stuff in there -- do you have legal issues?
malborodog
·3 năm trước·discuss
+1 for hermitix -- funny to see it come up on HN!
malborodog
·3 năm trước·discuss
Absolutely glorious. thx
malborodog
·3 năm trước·discuss
How could this underlying idea be implemented in a python script from a running selenium driver?
malborodog
·3 năm trước·discuss
What’s the infamous Dropbox comment? Sounds hilarious.
malborodog
·3 năm trước·discuss
Can't use third party service -- compliance stuff. This is helpful though. Using another model to tidy it up -- maybe Alpaca -- could be an option too. Then we'll just do speaker separation etc. manually later.
malborodog
·3 năm trước·discuss
Hm, I'm on Mac so it takes up a bunch of ram and I'm not used to this workflow. good point though.
malborodog
·3 năm trước·discuss
I have to transcribe a tonne of Chinese interviews soonish -- any further thoughts or experiments you can think of? Maybe some preprocessing steps to the audio? For example, cut it into one minute chunks with some overlap, then transcribe those, so that it can't skip those bits...? Or can we finetune it on a library of Chinese mp3s + transcripts?
malborodog
·3 năm trước·discuss
why not just run whisper from the command line directly? Why put it into a docker container??
malborodog
·3 năm trước·discuss
Nah it was done kinda tastefully here and it’s helpful to know the comps
malborodog
·3 năm trước·discuss
Anyone know best way to punch up his function a little so it tees >> out both the q and a to a file? Like history but for chat gpt.
malborodog
·3 năm trước·discuss
Yep. This is such an obvious use case. Have you seen the best thing out there that does this? Where can I load 100gb of pdfs and ask questions about what's in them??
malborodog
·3 năm trước·discuss
What's the startup?
malborodog
·3 năm trước·discuss
Just because it produces sequences of tokens that we typically experience as evidence of reasoning does not mean that it reasoned to produce them. We know -- generally -- the process by which those tokens were produced. It is not deterministic, but its properties are understood. It's a language model! It is not a mind.
malborodog
·3 năm trước·discuss
Is it? Why does everyone dunk on him?
malborodog
·3 năm trước·discuss
Link to the 990 dead — should have used archive.org or something.
malborodog
·3 năm trước·discuss
+1 for interest there
malborodog
·3 năm trước·discuss
Why isn't it easily dealt with by doing that??