Dataflow matrix machines (by Anhinga anhinga) (
dmm
) wrote
2023
-
02
-
05
01:25 am
Entry tags:
ai safety
,
anthropic ai
,
artificial intelligence
,
machine learning
,
transformers
,
understanding internals of ai
Technical interview with Neel Nanda
www.lesswrong.com/posts/r2yTwkGt3kbQG2mXi/axrp-episode-19-mechanistic-interpretability-with-neel-nanda
Threaded
|
Flat
no subject
dmm
2023-02-05 06:29 am (UTC)
(
link
)
This is a Feb 3 interview.
Neel Nanda solved the mystery of "Grokking" as an independent researcher.
Before that he co-authored other cool papers about internal mechanisms of Transformer-based models while at Anthropic AI.
(no subject)
dmm
-
2023-02-05 06:30 (UTC)
-
Expand
(no subject)
dmm
-
2023-02-05 06:31 (UTC)
-
Expand
3 comments
Post a new comment
Threaded
|
Flat
[
Home
|
Post Entry
|
Log in
|
Search
|
Browse Options
|
Site Map
]
![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
no subject
Neel Nanda solved the mystery of "Grokking" as an independent researcher.
Before that he co-authored other cool papers about internal mechanisms of Transformer-based models while at Anthropic AI.
(no subject)
(no subject)