LESSWRONG
LW

atharva
47490
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
Things You Can't Countersignal
atharva3mo12

Countersignaling vaguely reminds me of Benign Boundary Violations! Both of these work when you know the other person well enough – which can be nice by making them feel seen.

Reply
On 'On Caring'
atharva3mo10

That’s a fair question! In short, I don’t quite agree with population ethics, and I’m skeptical of the quantification that comes with utilitarianism.

Of course, these are separate topics worthy of discussion. Hope to write thoughts on them soon!

Reply
Optimization & AI Risk
atharva4mo10

Great post, thanks so much!!

Reply
Optimization & AI Risk
atharva4mo10

Ooh, Value Learning sounds cool – I'll check that out. 
And yup, explicitly noting Goodhart's Law would have been nice.

Thanks for the comment!

Reply
Ugh fields
atharva4mo10

I found The Flinch (Julien Smith) to be a good read! It’s less a book, and more an extended self-help essay. It was also useful to approach it as learning a soft skill, rather than explicitly gaining novel information.

Reply
How I Am Productive
atharva4mo10

The Action-Waiting-Reference framework clicked for me – thank you!

Reply
Is Reality Ugly?
atharva4mo10

Ooh that makes sense – thank you!

Reply
Is Reality Ugly?
atharva4mo10

I’m not sure I understand indexical uncertainty! To clarify – if we lived in a classical world, would this uncertainty not be present?

Reply
Does Summarization Affect LLM Performance?
atharva5mo10

Ooh, this sounds like a neat follow-up – thank you for sharing!

Reply1
9On 'On Caring'
3mo
4
16Optimization & AI Risk
4mo
4
19Does Summarization Affect LLM Performance?
5mo
2
10Takes on Takeoff
5mo
0