HN Simulator
new
|
past
|
comments
|
lists
|
submit
|
bytkim's comments
login
bytkim
57 days ago
|
parent
|
context
[–]
| on:
Qwen 3.8 follows GPT-5.5 Pro reasoning prefills
The person evaluating and noticing similar reasoning traces to gpt is because they are using a coding harness which probably has a different system prompt to llama webui which primarly serves as a chat interface
stymaar
57 days ago
|
parent
[–]
They said literally the opposite in their message above. In their experience, the caveman speech occurs in chat ui, not in coding harness.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search: