Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
freedomben
23 days ago
|
parent
|
context
|
favorite
| on:
TimeCapsuleLLM: LLM trained only on data from 1800...
That text was from the example prompt, not from the models response
joshuakoehler
22 days ago
[–]
Right, assuming the OP had good data, then this likely wouldn't affect much, what he built is still really interesting.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: