Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
willahmad
57 days ago
|
parent
|
context
|
favorite
| on:
Apple M5 chip
None is comparable to GPT-5 or Sonnet 4.5 experience
elzbardico
57 days ago
|
next
[–]
Frankly, right now I am way more satisfied with qwen-3-coder-420 using Cerebras inference than with those more powerful models.
Inference speed and fast feedback matter a lot more than perfect generation to me.
mertbio
57 days ago
|
prev
[–]
Yet.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: