Effective Altruism ForumEA Forum

Best of the Forum

People directory

Groups directory

How to use the Forum

Forum events calendar

EA Forum Podcast

Comments

Comments

Sorted by

New & upvoted

No comments on this post yet.

Be the first to respond.

Why and When Interpretability Work is Dangerous — EA Forum

Why and When Interpretability Work is Dangerous

1 min read·May 28, 2023

6

AI interpretability

AI interpretability

3 more

6

More from the author

71

[SEE EDIT] No, *You* Need to Write Clearer

NicholasKross·3y ago·1m read

·3y ago·1m read

43

Quick Thoughts on A.I. Governance

NicholasKross·4y ago·2m read

·4y ago·2m read

38

Effective Altruism, Before the Memes Started

NicholasKross·4y ago·12m read

·4y ago·12m read

Recent opportunities to take action

568

EA and the current funding situation

William_MacAskill·4y ago·28m read

William_MacAskill

·4y ago·28m read

395

Concrete Biosecurity Projects (some of which could be big)

ASB, eca·4y ago·6m read

+ 1 more

·4y ago·6m read

275

Announcing a contest: EA Criticism and Red Teaming

Lizka, finm, jtm·4y ago·16m read

Lizka, finm, jtm

+ 2 more

·4y ago·16m read