Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
grey-area
16 days ago
|
parent
|
context
|
favorite
| on:
The case for zero-error horizons in trustworthy LL...
It does matter because the LLM doesn’t always know when to use tools (e.g. ask it for sales projections which are similar to something in its weights) and is unable to reason about the boundaries of its knowledge.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: