LESSWRONG
LW

DanielFilan
8873Ω186815113798
Message
Dialogue
Subscribe

Sequences

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
AXRP - the AI X-risk Research Podcast
18DanielFilan's Shortform Feed
Ω
6y
Ω
166
The Cult of Pain
DanielFilan3d160

fun fact: more people die of heat in Europe per year than Americans who die of guns.

Reply
Authors Have a Responsibility to Communicate Clearly
DanielFilan8d33

I think he's using sloppy language.

Bengio et al. mix up "the policy/AI/agent is trained with RL and gets a high (maximal?) score on the training distribution" and "the policy/AI/agent is trained such that it wants to maximize reward (or some correlates) even outside of training".

Wait, does the friend elsewhere add "... and the author is right" or "and sloppiness isn't that bad"? My read of the quote you've provided is a critique and isn't excusing the sloppiness.

Reply
Beware General Claims about “Generalizable Reasoning Capabilities” (of Modern AI Systems)
DanielFilan24dΩ220

Ironically, given that it's currently June 11th (two days after my last tweet was posted) my final tweet provides two examples of the planning fallacy.

"Hopefully" is not a prediction!

Reply
Chris Olah’s views on AGI safety
DanielFilan1mo30

Sort of? Indeed this is more accessible to smaller groups than training big models, but small groups don't have access to the biggest models, and you can still do a bunch of non-mechinterpy things with the models you do have, so the effect isn't super overwhelming.

Reply
Elizabeth's Shortform
DanielFilan2mo63

(In case this isn't a joke, Mars Hill church was named after Mars Hill / the Areopagus / Hill of Ares, which in the New Testament is where the apostle Paul gives a speech to a bunch of pagans about Jesus. That hill is named after the Greek god. The church was located on Earth, in particular in Seattle.)

Reply
Consider not donating under $100 to political candidates
DanielFilan2mo40

Note that this post does not encourage people to withhold being politically active, or to totally refrain from making political donations.

Reply
Consider not donating under $100 to political candidates
DanielFilan2mo63

I don't know. I would imagine it's more like "it's bad to donate to the 'wrong' party" than "it's good to donate to the 'right' party".

Reply
MATS mentor selection
DanielFilan5mo20

In this comment we list the names of some of our advisors.

Reply
MATS mentor selection
DanielFilan5mo20

In this comment we list the names of some of our advisors.

Reply1
MATS mentor selection
DanielFilan5mo202

Below is a list of some of the advisors we used for mentor selection. Notes:

  • Two advisors asked not to be named and do not appear here.
  • Advisors by and large focussed their efforts on areas they had some expertise in.
  • Advisors had to flag conflicts of interest, meaning that (for example) we did not take their ratings of themselves into account.

With that out of the way, here are some advisors who helped us for the Winter 2024-25 cohort:

  • Adam Gleave
  • Alex Lawsen
  • Buck Shlegeris
  • Ethan Perez
  • Lawrence Chan
  • Lee Sharkey
  • Lewis Hammond
  • Marius Hobbhahn
  • Michael Aird
  • Neel Nanda

The above people also advised us for the Summer 2025 cohort. We also added the below advisors for that cohort:

  • Alexander Gietelink Oldenziel
  • Ben Garfinkel
  • Caspar Oesterheld
  • Jesse Clifton
  • Nate Thomas
Reply
Load More
Deceptive Alignment
2y
Singular Learning Theory
2y
(+159)
Singular Learning Theory
2y
(+6/-8)
Singular Learning Theory
2y
(+31/-1)
Singular Learning Theory
2y
(+101)
AXRP
3y
(+13/-4)
Center for Human-Compatible AI (CHAI)
5y
(+6/-6)
31AXRP Episode 45 - Samuel Albanie on DeepMind’s AGI Safety Approach
Ω
3d
Ω
0
12AXRP Episode 44 - Peter Salib on AI Rights for Human Safety
Ω
11d
Ω
0
12AXRP Episode 43 - David Lindner on Myopic Optimization with Non-myopic Approval
Ω
24d
Ω
0
12AXRP Episode 42 - Owain Evans on LLM Psychology
Ω
1mo
Ω
0
28AXRP Episode 41 - Lee Sharkey on Attribution-based Parameter Decomposition
Ω
1mo
Ω
1
136Consider not donating under $100 to political candidates
2mo
32
26AXRP Episode 40 - Jason Gross on Compact Proofs and Interpretability
Ω
3mo
Ω
0
13AXRP Episode 38.8 - David Duvenaud on Sabotage Evaluations and the Post-AGI Future
4mo
0
10AXRP Episode 38.7 - Anthony Aguirre on the Future of Life Institute
5mo
0
10AXRP Episode 38.6 - Joel Lehman on Positive Visions of AI
Ω
5mo
Ω
0
Load More