Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
segmondy
11 months ago
|
parent
|
context
|
favorite
| on:
Qwen3-Coder: Agentic coding in the world
i'm not willing to trade any more quality for performance. no draft, no cache for kv either. i'll take the performance cost, it just makes me think carefully about my prompt. i rarely every need more than one prompt to get my answers. :D
jychang
11 months ago
|
next
[–]
Speculative decoding doesn't change output tokens.
zackangelo
11 months ago
|
prev
[–]
Draft model doesn’t degrade quality!
segmondy
11 months ago
|
parent
[–]
I beg to differ, especially when it comes to code.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: