Convergence (org)

TagLast edit: 9 May 2023 15:11 UTC by Elliot_Mckernon

Convergence Analysis is an X-risk impact organisation focused on AI strategy research.

Machine Evolution

Justin Bullock, Elliot_Mckernon and cwdicarlo

11 Sep 2023 19:29 UTC

9 points

1 comment22 min readLW link

GPT-7: The Tale of the Big Computer (An Experimental Story)

Justin Bullock10 Jul 2023 20:22 UTC

4 points

4 comments5 min readLW link

The risk-reward tradeoff of interpretability research

JustinShovelain and Elliot_Mckernon

5 Jul 2023 17:05 UTC

14 points

1 comment6 min readLW link

Aligning AI by optimizing for “wisdom”

JustinShovelain and Elliot_Mckernon

27 Jun 2023 15:20 UTC

20 points

7 comments12 min readLW link

Improving the safety of AI evals

JustinShovelain and Elliot_Mckernon

17 May 2023 22:24 UTC

9 points

7 comments7 min readLW link

Keep humans in the loop

JustinShovelain and Elliot_Mckernon

19 Apr 2023 15:34 UTC

20 points

1 comment10 min readLW link

Updating Utility Functions

JustinShovelain and Joar Skalse

9 May 2022 9:44 UTC

37 points

6 comments8 min readLW link

Goodhart’s Law Causal Diagrams

JustinShovelain and Jeremy Gillen

11 Apr 2022 13:52 UTC

32 points

5 comments6 min readLW link

Using vector fields to visualise preferences and make them consistent

MichaelA and JustinShovelain

28 Jan 2020 19:44 UTC

41 points

32 comments11 min readLW link

No comments.