Viewing profile — malborodog
malborodog
HN member- Joined
- Sat, Oct 22, 2022, 10:54 PM UTC
- HN karma
- 36
- Public activity
- 57 items
- HN profile
- View on Hacker News ↗
About malborodog
No profile information was provided.
Recent public activity
-
comment
Comment #35476175
I am going to ask gpt 4 to implement this for me so I can see what it looks like. Amazing.
-
comment
Comment #35467217
why not just have a tonne of html files on disk?? I'm confused at why this requires a sophisticated backend.
-
comment
Comment #35466775
(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 …
-
comment
Comment #35421742
+1 for hermitix -- funny to see it come up on HN!
-
comment
Comment #35417488
Absolutely glorious. thx
-
comment
Comment #35405669
How could this underlying idea be implemented in a python script from a running selenium driver?
-
comment
Comment #35405652
What’s the infamous Dropbox comment? Sounds hilarious.
-
comment
Comment #35397180
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 s…
-
comment
Comment #35369534
Hm, I'm on Mac so it takes up a bunch of ram and I'm not used to this workflow. good point though.
-
comment
Comment #35369385
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…
-
comment
Comment #35367179
why not just run whisper from the command line directly? Why put it into a docker container??
-
comment
Comment #35356732
Nah it was done kinda tastefully here and it’s helpful to know the comps
-
comment
Comment #35356502
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.
-
comment
Comment #35353406
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??
-
comment
Comment #35353106
What's the startup?
-
comment
Comment #35339325
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 proce…
-
comment
Comment #35335486
Is it? Why does everyone dunk on him?
-
comment
Comment #35323452
Link to the 990 dead — should have used archive.org or something.
-
comment
Comment #35308621
+1 for interest there
-
comment
Comment #35302469
Why isn't it easily dealt with by doing that??
-
comment
Comment #35300837
Someone still has to talk to the computer and make it do stuff. That’s us. That won’t change even if how we do it changes.
-
comment
Comment #35287389
Beautiful. Got it; thank you.
-
comment
Comment #35273466
When you say text indexing and serving http are library functions, what do you mean? Also, is the language here go or what? Since you said python is too slow and then necessitates …
-
comment
Comment #35273315
Can you explain that again differently? I didn’t understand that captcha point. It feels important though.
-
comment
Comment #35241606
Implementation details. Check out what's going on with LangChain, augmented retrieval, etc. We'll be able to create knowledge bases on specific subjects with vetted data, and get t…