Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
Vintage Large Language Models
(
owainevans.github.io
)
80 points
by
pr337h4m
1 day ago
|
past
|
26 comments
The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A” [pdf]
(
owainevans.github.io
)
1 point
by
rbanffy
on Sept 25, 2023
|
past
The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A” [pdf]
(
owainevans.github.io
)
3 points
by
artninja1988
on Sept 23, 2023
|
past
|
2 comments
The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A” [pdf]
(
owainevans.github.io
)
3 points
by
mellosouls
on Sept 22, 2023
|
past
|
5 comments
TruthfulQA: Measuring How Models Mimic Human Falsehoods [pdf]
(
owainevans.github.io
)
2 points
by
todsacerdoti
on Sept 18, 2021
|
past
Trial Without Error: Towards Safe RL with Human Intervention
(
owainevans.github.io
)
2 points
by
rmorey
on Oct 7, 2017
|
past
|
1 comment
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
