Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
throwaway198846
4 months ago
|
parent
|
context
|
favorite
| on:
The behavior of LLMs in hiring decisions: Systemic...
I wonder why Deepseek V3 stands out as significantly less biased in some of those tests, what is special about it?
ramoz
4 months ago
[–]
Rough guess - they worked hard to filter out American cultural influence and related social academics.
throwaway198846
4 months ago
|
parent
|
next
[–]
Deepseek R1 doesn't do as well as V3 so I don't think it is that simple
Ancapistani
4 months ago
|
root
|
parent
|
next
[–]
Isn't it at least rumored that -R1 was trained and/or fine-tuned on outputs from ChatGPT?
If so, and if -V3 was not, that would make sense to me.
Xunjin
4 months ago
|
parent
|
prev
[–]
How did you come by this guess?
Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
