LESSWRONG
LW

BraydenM
16413290
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
AI Control: Improving Safety Despite Intentional Subversion
BraydenM8mo103Review for 2023 Review

Was a widely impactful piece of work, beyond the bounds of the less wrong community

Reply
RSPs are pauses done right
BraydenM2y96

My guess is that the hard "Pause" advocates are focussed on optimizing for actions that are "necessary" and "sufficient" for safety, but at the expense of perhaps not being politically or practically "feasible".

Whereas, "Responsible Scaling Policies" advocates may instead describe actions that are "necessary", and more "feasible" however are less likely to be "sufficient".

The crux of this disagreement might be related to how feasible, or how sufficient each of these two pathways respectively are?

Absent any known pathways that solve all three, I'm glad people are exploring both of these pathways (and the potential overlap between them). I hope that there is increased exploration. 

Perhaps we are going through a temporary phase of increased contention between Pauses versus RSPs as they both may be vying for similar memetic uptake (e.g. on the lesswrong home page right now there is a link for "Global Pause AI Protest" events spread across seven countries happening a few days from now.)

(Conflict of interest: I support implementation of Anthropic's Responsible Scaling Policy)

Reply
AI #1: Sydney and Bing
BraydenM3y60

Thanks for interesting post as usual, Zvi. As one of the new members of the Product team at Anthropic that you referenced (and commenting in a personal capacity, not representing my employer) I would like to offer that I endorse collaborative (or at least, communicative) community norms and I personally aim to regularly engage with folks across the community.

This week I will be talking to folks in person at the Berkeley AI impacts dinner, and at EAG Berkeley this weekend. I hope to meet some of you there.

Reply
Meetup : San Francisco Meetup
BraydenM11y00

I'll be there!

Reply
Community overview and resources for modern Less Wrong meetup organisers
BraydenM11y00

This content should probably be a wiki page, linked to the other meetup resources, right?

Reply
Meetup : Stanford Salon and LW inaugural meetup
BraydenM11y20

Update: the official kick off time is 7:30pm, but guests are invited to arrive from 7pm onwards.

Reply
Meetup : Stanford Salon and LW inaugural meetup
BraydenM11y40

This event is open to all

Reply
Community overview and resources for modern Less Wrong meetup organisers
BraydenM11y20

I'd like to gauge feedback, see how useful other organisers expect this information to be, and see if other organisers would be interested in contributing first, but in general, Yes.

Reply
LessWrong Help Desk - free paper downloads and more (2014)
BraydenM12y10

Can anyone help with this one: Nonsocial Transient Behavior: Social Disengagement on the Greyhound Bus

Reply
Meetup : Melbourne Social Meetup
BraydenM12y10

See you all there!

Reply
Load More
5Meetup : Stanford Salon and LW inaugural meetup
11y
4
26Community overview and resources for modern Less Wrong meetup organisers
11y
3
2Meetup : Melbourne Social Southern Summer Solstice Celebration
12y
0
1Meetup : December Practical Rationality Meetup
12y
2
4Meetup : Sunday Brunch Club - Sunday 20th October
12y
1
3Meetup : Melbourne Practical Rationality Meetup
12y
0
1Meetup : Melbourne Practical Rationality: Group Prediction Calibration and Aumann's Agreement Theorem
12y
0
2Meetup : Melbourne Excursion: Comfort Zone Expansion
12y
5
1Meetup : Melbourne Practical Rationality - July 5th
12y
1
2Meetup : Melbourne LW Outing: Astronomy evening in Eltham, Saturday 29th June, 5:30pm
12y
0
Load More