RSS

Rafael Harth

Karma: 4,217

I’m an independent researcher currently working on a sequence of posts about consciousness. You can send me anonymous feedback here: https://​​www.admonymous.co/​​rafaelharth. If it’s about a post, you can add [q] or [nq] at the end if you want me to quote or not quote it in the comment section.

In­ner Align­ment: Ex­plain like I’m 12 Edition

Rafael Harth1 Aug 2020 15:24 UTC
179 points
46 comments13 min readLW link2 reviews

How to eval­u­ate (50%) predictions

Rafael Harth10 Apr 2020 17:12 UTC
134 points
50 comments9 min readLW link

[Question] How to think about and deal with OpenAI

Rafael Harth9 Oct 2021 13:10 UTC
107 points
68 comments1 min readLW link

The case for Do­ing Some­thing Else (if Align­ment is doomed)

Rafael Harth5 Apr 2022 17:52 UTC
93 points
14 comments2 min readLW link

Why it’s so hard to talk about Consciousness

Rafael Harth2 Jul 2023 15:56 UTC
81 points
151 comments9 min readLW link

A guide to Iter­ated Am­plifi­ca­tion & Debate

Rafael Harth15 Nov 2020 17:14 UTC
75 points
12 comments15 min readLW link

Not-Use­less Ad­vice For Deal­ing With Things You Don’t Want to Do

Rafael Harth4 Apr 2022 16:37 UTC
53 points
10 comments6 min readLW link

In­sights from Lin­ear Alge­bra Done Right

Rafael Harth13 Jul 2019 18:24 UTC
53 points
18 comments9 min readLW link

We tend to for­get com­pli­cated things

Rafael Harth20 Oct 2019 20:05 UTC
48 points
15 comments1 min readLW link

The “AI Dun­geons” Dragon Model is heav­ily path de­pen­dent (test­ing GPT-3 on ethics)

Rafael Harth21 Jul 2020 12:14 UTC
44 points
9 comments6 min readLW link

Un­der­stand­ing Ma­chine Learn­ing (I)

Rafael Harth20 Dec 2019 18:22 UTC
44 points
12 comments11 min readLW link

[Question] Do you vote based on what you think to­tal karma should be?

Rafael Harth24 Aug 2020 13:37 UTC
43 points
57 comments1 min readLW link

Pre­face to the Se­quence on Fac­tored Cognition

Rafael Harth30 Nov 2020 18:49 UTC
35 points
6 comments2 min readLW link

Ideal­ized Fac­tored Cognition

Rafael Harth30 Nov 2020 18:49 UTC
34 points
6 comments11 min readLW link

A Sim­ple In­tro­duc­tion to Neu­ral Networks

Rafael Harth9 Feb 2020 22:02 UTC
34 points
13 comments18 min readLW link

Ex­is­ten­tial Risk is a sin­gle category

Rafael Harth9 Aug 2020 17:47 UTC
31 points
7 comments1 min readLW link

In­sights from Munkres’ Topology

Rafael Harth17 Mar 2019 16:52 UTC
30 points
0 comments14 min readLW link

Hid­ing Complexity

Rafael Harth20 Nov 2020 16:35 UTC
29 points
14 comments7 min readLW link

In­for­ma­tion Charts

Rafael Harth13 Nov 2020 16:12 UTC
29 points
6 comments13 min readLW link

Intuition

Rafael Harth20 Dec 2020 21:49 UTC
26 points
1 comment6 min readLW link