Apart Research

TagLast edit: 22 Oct 2022 1:49 UTC by habryka

Apart Research is a research organization working on AI Alignment. This tag includes posts written by Apart researchers, and content about Apart Research.

Results from the interpretability hackathon

Esben Kran and Neel Nanda

17 Nov 2022 14:51 UTC

81 points

0 comments6 min readLW link

(alignmentjam.com)

Black Box Investigation Research Hackathon

Esben Kran and Jonas Hallgren

12 Sep 2022 7:20 UTC

9 points

4 comments2 min readLW link

Newsletter for Alignment Research: The ML Safety Updates

Esben Kran22 Oct 2022 16:17 UTC

16 points

0 comments1 min readLW link

AI & ML Safety Updates W43

Esben Kran and Steinthal

28 Oct 2022 13:18 UTC

9 points

3 comments3 min readLW link

AI Safety Ideas: An Open AI Safety Research Platform

Esben Kran17 Oct 2022 17:01 UTC

24 points

0 comments1 min readLW link

Safety timelines: How long will it take to solve alignment?

Esben Kran, JonathanRystroem and Steinthal

19 Sep 2022 12:53 UTC

36 points

7 comments6 min readLW link

(forum.effectivealtruism.org)

Results from the language model hackathon

Esben Kran10 Oct 2022 8:29 UTC

22 points

1 comment4 min readLW link

Join the interpretability research hackathon

Esben Kran28 Oct 2022 16:26 UTC

15 points

0 comments1 min readLW link

[Book] Interpretable Machine Learning: A Guide for Making Black Box Models Explainable

Esben Kran31 Oct 2022 11:38 UTC

19 points

1 comment1 min readLW link

(christophm.github.io)

Can we predict the abilities of future AI? MLAISU W44

Esben Kran and Steinthal

4 Nov 2022 15:19 UTC

10 points

0 comments3 min readLW link

(newsletter.apartresearch.com)

Are funding options for AI Safety threatened? W45

Steinthal, Esben Kran and Sabrina Zaki

11 Nov 2022 13:00 UTC

7 points

0 comments3 min readLW link

(newsletter.apartresearch.com)

How Should AIS Relate To Its Funders? W46

Steinthal, Esben Kran and Sabrina Zaki

21 Nov 2022 15:58 UTC

6 points

1 comment3 min readLW link

(newsletter.apartresearch.com)

NeurIPS Safety & ChatGPT. MLAISU W48

Esben Kran and Steinthal

2 Dec 2022 15:50 UTC

3 points

0 comments4 min readLW link

(newsletter.apartresearch.com)

ML Safety at NeurIPS & Paradigmatic AI Safety? MLAISU W49

Esben Kran and Steinthal

9 Dec 2022 10:38 UTC

19 points

0 comments4 min readLW link

(newsletter.apartresearch.com)

Join the AI Testing Hackathon this Friday

Esben Kran12 Dec 2022 14:24 UTC

10 points

0 comments1 min readLW link

Will Machines Ever Rule the World? MLAISU W50

Esben Kran16 Dec 2022 11:03 UTC

12 points

7 comments4 min readLW link

(newsletter.apartresearch.com)

AI improving AI [MLAISU W01!]

Esben Kran6 Jan 2023 11:13 UTC

5 points

0 comments4 min readLW link

(newsletter.apartresearch.com)

Robustness & Evolution [MLAISU W02]

Esben Kran13 Jan 2023 15:47 UTC

10 points

0 comments3 min readLW link

(newsletter.apartresearch.com)

Generalizability & Hope for AI [MLAISU W03]

Esben Kran20 Jan 2023 10:06 UTC

5 points

2 comments2 min readLW link

(newsletter.apartresearch.com)

Decentralized Research & ChatGPT [MLAISU W04]

Esben Kran27 Jan 2023 13:55 UTC

3 points

0 comments3 min readLW link

(newsletter.apartresearch.com)

Oversight and AI risk [MLAISU W05]

Esben Kran and Fazl

6 Feb 2023 12:26 UTC

4 points

0 comments2 min readLW link

(newsletter.apartresearch.com)

Arms Race Dynamics [MLAISU W06]

Esben Kran and Fazl

10 Feb 2023 13:20 UTC

5 points

0 comments3 min readLW link

(newsletter.apartresearch.com)

We Found An Neuron in GPT-2

Joseph Miller and Clement Neo

11 Feb 2023 18:27 UTC

136 points

21 comments7 min readLW link

(clementneo.com)

Bing misalignment [MLAISU W07]

Esben Kran and Fazl

21 Feb 2023 9:02 UTC

5 points

0 comments3 min readLW link

(newsletter.apartresearch.com)

Automated Sandwiching & Quantifying Human-LLM Cooperation: ScaleOversight hackathon results

Esben Kran, Fazl, Sabrina Zaki, gabrielrecc and rz2383

23 Feb 2023 10:48 UTC

8 points

0 comments6 min readLW link

RL Interpretability & Perspectives on AI Safety [MLAISU W08-09]

Esben Kran and Fazl

6 Mar 2023 23:52 UTC

5 points

0 comments4 min readLW link

GPT-4 & Japanese Alignment [MLAISU W10]

Esben Kran and Fazl

15 Mar 2023 18:07 UTC

7 points

0 comments4 min readLW link

(newsletter.apartresearch.com)

No comments.