Team

Justin Shovelain

Chairman & Senior Strategist

Justin is Chief Strategist and Co-Founder of Convergence. He is an AI safety advisor to Lionheart Ventures. He has worked with existential risk research since 2009, including working with MIRI, CFAR, EA Global, and Founders Fund. He has done work in EA strategy, fundraising, networking, teaching, cognitive enhancement, and AI safety research. He has an MS degree in computer science and BS degrees in computer science, mathematics, and physics.

Publications

Research Agenda

AI Clarity: An Initial Research Agenda

Justin Bullock, Corin Katzke, Zershaaneh Qureshi, David Kristoffersson

Apr 16, 2024

13

minute read

Research Agenda

AI Clarity: An Initial Research Agenda

Justin Bullock, Corin Katzke, Zershaaneh Qureshi, David Kristoffersson

Apr 16, 2024

13

minute read

Research Agenda

AI Clarity: An Initial Research Agenda

Justin Bullock, Corin Katzke, Zershaaneh Qureshi, David Kristoffersson

Apr 16, 2024

13

minute read

Technical AI Safety

Information-Theoretic Boxing of Superintelligences

Justin Shovelain, Elliot McKernon

Nov 30, 2023

9

minute read

Technical AI Safety

Information-Theoretic Boxing of Superintelligences

Justin Shovelain, Elliot McKernon

Nov 30, 2023

9

minute read

Technical AI Safety

Information-Theoretic Boxing of Superintelligences

Justin Shovelain, Elliot McKernon

Nov 30, 2023

9

minute read

Value Modeling

Aligning AI by optimizing for "wisdom"

Justin Shovelain, Elliot McKernon

Jun 27, 2023

14

minute read

Value Modeling

Aligning AI by optimizing for "wisdom"

Justin Shovelain, Elliot McKernon

Jun 27, 2023

14

minute read

Value Modeling

Aligning AI by optimizing for "wisdom"

Justin Shovelain, Elliot McKernon

Jun 27, 2023

14

minute read

Mitigating Existential Risks

Improving the safety of AI evals

Justin Shovelain, Elliot McKernon

Jun 18, 2023

8

minute read

Mitigating Existential Risks

Improving the safety of AI evals

Justin Shovelain, Elliot McKernon

Jun 18, 2023

8

minute read

Mitigating Existential Risks

Improving the safety of AI evals

Justin Shovelain, Elliot McKernon

Jun 18, 2023

8

minute read

Technical AI Safety

The risk-reward tradeoff of interpretability research

Justin Shovelain, Elliot McKernon

Jun 5, 2023

7

minute read

Technical AI Safety

The risk-reward tradeoff of interpretability research

Justin Shovelain, Elliot McKernon

Jun 5, 2023

7

minute read

Technical AI Safety

The risk-reward tradeoff of interpretability research

Justin Shovelain, Elliot McKernon

Jun 5, 2023

7

minute read

Mitigating Existential Risks

Keep humans in the loop

Justin Shovelain, Elliot McKernon

Apr 19, 2023

11

minute read

Mitigating Existential Risks

Keep humans in the loop

Justin Shovelain, Elliot McKernon

Apr 19, 2023

11

minute read

Mitigating Existential Risks

Keep humans in the loop

Justin Shovelain, Elliot McKernon

Apr 19, 2023

11

minute read

Value Modeling

Updating Utility Functions

Justin Shovelain, Joar Skalse

May 9, 2022

9

minute read

Value Modeling

Updating Utility Functions

Justin Shovelain, Joar Skalse

May 9, 2022

9

minute read

Value Modeling

Updating Utility Functions

Justin Shovelain, Joar Skalse

May 9, 2022

9

minute read

Technical AI Safety

Goodhart's Law Causal Diagrams

Justin Shovelain, Jeremy Gillen

Apr 11, 2022

7

minute read

Technical AI Safety

Goodhart's Law Causal Diagrams

Justin Shovelain, Jeremy Gillen

Apr 11, 2022

7

minute read

Technical AI Safety

Goodhart's Law Causal Diagrams

Justin Shovelain, Jeremy Gillen

Apr 11, 2022

7

minute read

Strategy Research Tooling

Four components of strategy research

Michael Aird, Justin Shovelain, David Kristoffersson, Siebe Rozendal

Jan 31, 2021

6

minute read

Strategy Research Tooling

Four components of strategy research

Michael Aird, Justin Shovelain, David Kristoffersson, Siebe Rozendal

Jan 31, 2021

6

minute read

Strategy Research Tooling

Four components of strategy research

Michael Aird, Justin Shovelain, David Kristoffersson, Siebe Rozendal

Jan 31, 2021

6

minute read

Strategy Research Tooling

Evaluating expertise: a clear box model

Justin Shovelain

Oct 15, 2020

6

minute read

Strategy Research Tooling

Evaluating expertise: a clear box model

Justin Shovelain

Oct 15, 2020

6

minute read

Strategy Research Tooling

Evaluating expertise: a clear box model

Justin Shovelain

Oct 15, 2020

6

minute read

Strategy Research Tooling

Improving the future by influencing actors' benevolence, intelligence, and power

Michael Aird, Justin Shovelain

Jul 20, 2020

21

minute read

Strategy Research Tooling

Improving the future by influencing actors' benevolence, intelligence, and power

Michael Aird, Justin Shovelain

Jul 20, 2020

21

minute read

Strategy Research Tooling

Improving the future by influencing actors' benevolence, intelligence, and power

Michael Aird, Justin Shovelain

Jul 20, 2020

21

minute read

Downside Risks

Good and bad ways to think about downside risks

Michael Aird, Justin Shovelain

Jun 11, 2020

13

minute read

Downside Risks

Good and bad ways to think about downside risks

Michael Aird, Justin Shovelain

Jun 11, 2020

13

minute read

Downside Risks

Good and bad ways to think about downside risks

Michael Aird, Justin Shovelain

Jun 11, 2020

13

minute read

Risk Modeling

Causal diagrams of the paths to existential catastrophe

Michael Aird, Justin Shovelain, David Kristoffersson

Mar 1, 2020

15

minute read

Risk Modeling

Causal diagrams of the paths to existential catastrophe

Michael Aird, Justin Shovelain, David Kristoffersson

Mar 1, 2020

15

minute read

Risk Modeling

Causal diagrams of the paths to existential catastrophe

Michael Aird, Justin Shovelain, David Kristoffersson

Mar 1, 2020

15

minute read

Downside Risks

Memetic downside risks: How ideas can evolve and cause harm

Michael Aird, Justin Shovelain, algekalipso

Feb 26, 2020

18

minute read

Downside Risks

Memetic downside risks: How ideas can evolve and cause harm

Michael Aird, Justin Shovelain, algekalipso

Feb 26, 2020

18

minute read

Downside Risks

Memetic downside risks: How ideas can evolve and cause harm

Michael Aird, Justin Shovelain, algekalipso

Feb 26, 2020

18

minute read

Information Hazards

Information hazards: Why you should care and what you can do

Michael Aird, Justin Shovelain, David Kristoffersson, algekalipso

Feb 24, 2020

18

minute read

Information Hazards

Information hazards: Why you should care and what you can do

Michael Aird, Justin Shovelain, David Kristoffersson, algekalipso

Feb 24, 2020

18

minute read

Information Hazards

Information hazards: Why you should care and what you can do

Michael Aird, Justin Shovelain, David Kristoffersson, algekalipso

Feb 24, 2020

18

minute read

Information Hazards

Mapping downside risks and information hazards

Michael Aird, Justin Shovelain, David Kristoffersson

Feb 20, 2020

11

minute read

Information Hazards

Mapping downside risks and information hazards

Michael Aird, Justin Shovelain, David Kristoffersson

Feb 20, 2020

11

minute read

Information Hazards

Mapping downside risks and information hazards

Michael Aird, Justin Shovelain, David Kristoffersson

Feb 20, 2020

11

minute read

Value Modeling

Using vector fields to visualise preferences and make them consistent

Michael Aird, Justin Shovelain

Jan 29, 2020

14

minute read

Value Modeling

Using vector fields to visualise preferences and make them consistent

Michael Aird, Justin Shovelain

Jan 29, 2020

14

minute read

Value Modeling

Using vector fields to visualise preferences and make them consistent

Michael Aird, Justin Shovelain

Jan 29, 2020

14

minute read

Mitigating Existential Risks

AI alignment concepts: philosophical breakers, stoppers, and distorters

Justin Shovelain

Jan 25, 2020

4

minute read

Mitigating Existential Risks

AI alignment concepts: philosophical breakers, stoppers, and distorters

Justin Shovelain

Jan 25, 2020

4

minute read

Mitigating Existential Risks

AI alignment concepts: philosophical breakers, stoppers, and distorters

Justin Shovelain

Jan 25, 2020

4

minute read

Mitigating Existential Risks

Safety regulators: A tool for mitigating technological risk

Justin Shovelain

Jan 21, 2020

4

minute read

Mitigating Existential Risks

Safety regulators: A tool for mitigating technological risk

Justin Shovelain

Jan 21, 2020

4

minute read

Mitigating Existential Risks

Safety regulators: A tool for mitigating technological risk

Justin Shovelain

Jan 21, 2020

4

minute read

Strategy Research Tooling

The 'sprinting between oases' strategy

Justin Shovelain

Jan 16, 2020

2

minute read

Strategy Research Tooling

The 'sprinting between oases' strategy

Justin Shovelain

Jan 16, 2020

2

minute read

Strategy Research Tooling

The 'sprinting between oases' strategy

Justin Shovelain

Jan 16, 2020

2

minute read

Strategy Research Tooling

Moloch and the Pareto optimal frontier

Justin Shovelain

Jan 14, 2020

2

minute read

Strategy Research Tooling

Moloch and the Pareto optimal frontier

Justin Shovelain

Jan 14, 2020

2

minute read

Strategy Research Tooling

Moloch and the Pareto optimal frontier

Justin Shovelain

Jan 14, 2020

2

minute read

Holistic Strategy Research

A case for strategy research: what it is and why we need more of it

Siebe Rozendal, Justin Shovelain, David Kristoffersson

Jun 20, 2019

24

minute read

Holistic Strategy Research

A case for strategy research: what it is and why we need more of it

Siebe Rozendal, Justin Shovelain, David Kristoffersson

Jun 20, 2019

24

minute read

Holistic Strategy Research

A case for strategy research: what it is and why we need more of it

Siebe Rozendal, Justin Shovelain, David Kristoffersson

Jun 20, 2019

24

minute read

Risk Modeling

State Space of X-Risk Trajectories

David Kristoffersson, Justin Shovelain

Feb 6, 2020

4

minute read

Risk Modeling

State Space of X-Risk Trajectories

David Kristoffersson, Justin Shovelain

Feb 6, 2020

4

minute read

Risk Modeling

State Space of X-Risk Trajectories

David Kristoffersson, Justin Shovelain

Feb 6, 2020

4

minute read