adamShimi(Adam Shimi)

Karma: 5,845

Epistemologist specialized in the difficulties of alignment. Currently at Conjecture, and running Refine.

Goal-directed = Model-based RL?

adamShimi20 Feb 2020 19:13 UTC

21 points

10 comments3 min readLW link

Where’s the Turing Machine? A step towards Ontology Identification

adamShimi26 Feb 2020 17:10 UTC

25 points

0 comments8 min readLW link

Lessons from Isaac: Poor Little Robbie

adamShimi14 Mar 2020 17:14 UTC

1 point

8 comments3 min readLW link

Welcome to the Haskell Jungle

adamShimi18 Mar 2020 18:58 UTC

16 points

2 comments2 min readLW link

My Functor is Rich!

adamShimi18 Mar 2020 18:58 UTC

10 points

0 comments17 min readLW link

Lessons from Isaac: Pitfalls of Reason

adamShimi8 May 2020 20:44 UTC

9 points

0 comments8 min readLW link

Focus: you are allowed to be bad at accomplishing your goals

adamShimi3 Jun 2020 21:04 UTC

19 points

17 comments3 min readLW link

Goal-directedness is behavioral, not structural

adamShimi8 Jun 2020 23:05 UTC

6 points

12 comments3 min readLW link

Locality of goals

adamShimi22 Jun 2020 21:56 UTC

16 points

8 comments6 min readLW link

The 8 Techniques to Tolerify the Dark World

adamShimi20 Jul 2020 0:58 UTC

2 points

5 comments2 min readLW link

Dealing with Curiosity-Stoppers

adamShimi30 Jul 2020 22:05 UTC

50 points

6 comments10 min readLW link

[Question] What are you looking for in a Less Wrong post?

adamShimi1 Aug 2020 18:00 UTC

27 points

19 comments1 min readLW link

[Question] What are the most important papers/post/resources to read to understand more of GPT-3?

adamShimi2 Aug 2020 20:53 UTC

22 points

4 comments1 min readLW link

Analyzing the Problem GPT-3 is Trying to Solve

adamShimi6 Aug 2020 21:58 UTC

16 points

2 comments4 min readLW link

[Question] Will OpenAI’s work unintentionally increase existential risks related to AI?

adamShimi11 Aug 2020 18:16 UTC

53 points

55 comments1 min readLW link

Goal-Directedness: What Success Looks Like

adamShimi16 Aug 2020 18:33 UTC

9 points

0 comments2 min readLW link

Universality Unwrapped

adamShimi21 Aug 2020 18:53 UTC

29 points

2 comments18 min readLW link

The “Backchaining to Local Search” Technique in AI Alignment

adamShimi18 Sep 2020 15:05 UTC

29 points

1 comment2 min readLW link

Why You Should Care About Goal-Directedness

adamShimi9 Nov 2020 12:48 UTC

38 points

15 comments9 min readLW link

The (Unofficial) Less Wrong Comment Challenge

adamShimi11 Nov 2020 14:18 UTC

82 points

35 comments2 min readLW link