Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
catigula
17 days ago
|
parent
|
context
|
favorite
| on:
DeepSeek-v3.2: Pushing the frontier of open large ...
He means capturing things that benchmarks don't. You can use Claude and GPT-5 back-to-back in a field that score nearly identically on. You will notice several differences. This is the "vibe".
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: