Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mh-
on Aug 23, 2025
|
parent
|
context
|
favorite
| on:
Sprinkling self-doubt on ChatGPT
Yeah, sorry I was talking about the "why does saying no elephants cause elephants".
Phrasing it as do rather than don't is probably still more effective on both humans and LLMs. :)
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Phrasing it as do rather than don't is probably still more effective on both humans and LLMs. :)