Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
embedding-shape
3 months ago
|
parent
|
context
|
favorite
| on:
BitNet: Inference framework for 1-bit LLMs
Your worry about Wikipedia is that there is "much room for human error and bias", yet earlier you seem to imply that a LLM that has access to the www somehow would have less human error and bias? Personally, I'd see it the other way around.
giancarlostoro
3 months ago
[–]
When GPT 3.5 became a thing, it had crawled a very nuanced set of websites, this is what I mean. You basically curate where it sources data from.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: