Hacker Read
top
|
best
|
new
|
newcomments
|
leaders
|
about
|
bookmarklet
login
rileyphone | karma 1170 | avg karma 2.45
2024-06-13 06:40:46
|
next
[–]
update item
In that case there are two attractors - one towards the Golden Gate Bridge and one towards the harmless, helpful, honest assistant persona. Techniques as such probably get weirder results with model scale but no reason to think they get wiped out.
reply
view as:
tree
latest_first
coldtea | karma 86593 | avg karma 2.38
2024-06-13 09:05:02
|
next
[–]
similar comments
What if the Golden Gate Bridge is Main Kampf or something like that?
reply
Legal
|
privacy
reply