Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
AustinDev
9 months ago
|
parent
|
context
|
favorite
| on:
AI Blindspots – Blindspots in LLMs I've noticed wh...
Use claude 3.5 if you have detailed instructions that you want it to follow. I've found over many hours of using these models that 3.7 loves to go off-script no matter how many rules you provide.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: