344
this post was submitted on 25 Mar 2024
344 points (98.3% liked)
Technology
59021 readers
2956 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Yes training is the most expensive but it's still an additional trillion or so floating point operations per generated token of output. That's not nothing computationally.
Just consider how long it takes GPT4 to answer a question. Anywhere from a few seconds to a minute in my experience. There's at least one A100 at probably 400w going full throttle that whole time, plus all the supporting hardware.