Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
photochemsyn
25 days ago
|
parent
|
context
|
favorite
| on:
AI's Wrong Answers Are Bad. Its Wrong Reasoning Is...
If you specify a worldview and a context in the prompt, a lot of this can be avoided, but there don't seem to be any real failsafes.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: