Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
andy_ppp
4 months ago
|
parent
|
context
|
favorite
| on:
SpikingBrain 7B – More efficient than classic LLMs
I honestly thing they just styled it out as "more efficient" and their investors lapped it up. We've really not seen improvement since GPT4 for most things I do with is and it feels like a downgrade on o3-mini-high to me.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: