HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
nextaccountic
57 days ago
|
parent
|
context
|
favorite
| on:
Anthropic's ‘watermark’ text adulteration in Claud...
Reasoning tokens are a way to escape autoregressive woes. The model can generate a draft, then ponder on it, and use this to generate a final version
thatjoeoverthr
57 days ago
[–]
They’re a way to mitigate it. It still writes like an LLM and everyone can see it.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search: