Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nextworddev
6 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.2
Claude is pretty trash for anything besides coding
wyre
6 days ago
|
next
[–]
What are you basing that on? Between Sonnet and Opus I don't think I'm reaching for Gemini 3 at all.
reply
romanovcode
5 days ago
|
prev
|
next
[–]
Yeah, but that is the whole point of Claude. And that's why we are interested in the comparison.
reply
timmg
6 days ago
|
prev
[–]
That hasn't been my experience at all. I always wondered if we just get used to how to prompt a given model and that it hard to transition to another.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: