Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ComputerGuru
5 months ago
|
parent
|
context
|
favorite
| on:
GPT-5 for Developers
That is genuinely nice to see. What are you using for the embeddings?
pamelafox
5 months ago
[–]
We use text-embedding-3-large, with both quantization and MRL reduction, plus oversampling on the search to compensate for the compression.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: