Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
SparkyMcUnicorn
on Jan 26, 2025
|
parent
|
context
|
favorite
| on:
DeepSeek-R1: Incentivizing Reasoning Capability in...
Kagi is using fireworks.ai according to the docs, which is the 685B model.
Kagi and Aider benchmarks definitely put R1 in the lead, but I have yet to try them out.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Kagi and Aider benchmarks definitely put R1 in the lead, but I have yet to try them out.