richard_ngo

Former AI safety research engineer, now AI governance researcher at OpenAI. Blog: thinkingcomplete.blogspot.com

Posts

Defining alignment research
by richard_ngo @ 2024-08-19 | +48 | 0 comments
Twitter thread on open-source AI
by richard_ngo @ 2024-07-31 | +32 | 0 comments
Twitter thread on AI safety evals
by richard_ngo @ 2024-07-31 | +38 | 0 comments
Towards more cooperative AI safety strategies
by richard_ngo @ 2024-07-16 | +62 | 0 comments
You must not fool yourself, and you are the easiest person to fool
by richard_ngo @ 2023-07-08 | +25 | 0 comments
Agency begets agency
by richard_ngo @ 2023-07-06 | +28 | 0 comments
Cultivate an obsession with the object level
by richard_ngo @ 2023-06-07 | +24 | 0 comments
Coercion is an adaptation to scarcity; trust is an adaptation to abundance
by richard_ngo @ 2023-05-23 | +38 | 0 comments
Self-leadership and self-love dissolve anger and trauma
by richard_ngo @ 2023-05-22 | +29 | 0 comments
Trust develops gradually via making bids and setting boundaries
by richard_ngo @ 2023-05-19 | +25 | 0 comments
Resolving internal conflicts requires listening to what parts want
by richard_ngo @ 2023-05-19 | +23 | 0 comments
Conflicts between emotional schemas often involve internal coercion
by richard_ngo @ 2023-05-17 | +34 | 0 comments
We learn long-lasting strategies to protect ourselves from danger and rejection
by richard_ngo @ 2023-05-16 | +43 | 0 comments
Judgments often smuggle in implicit standards
by richard_ngo @ 2023-05-15 | +46 | 0 comments
From fear to excitement
by richard_ngo @ 2023-05-15 | +62 | 0 comments
Clarifying and predicting AGI
by richard_ngo @ 2023-05-04 | +69 | 0 comments
AGI safety career advice
by richard_ngo @ 2023-05-02 | +211 | 0 comments
Brainstorming ways to make EA safer and more inclusive
by richard_ngo @ 2022-11-15 | +149 | 0 comments
Alignment 201 curriculum
by richard_ngo @ 2022-10-12 | +94 | 0 comments
The alignment problem from a deep learning perspective
by richard_ngo @ 2022-08-11 | +58 | 0 comments
Moral strategies at different capability levels
by richard_ngo @ 2022-07-27 | +24 | 0 comments
Making decisions using multiple worldviews
by richard_ngo @ 2022-07-13 | +43 | 0 comments
Three intuitions about EA: responsibility, scale, self-improvement
by richard_ngo @ 2022-04-15 | +196 | 0 comments
Beyond micromarriages
by richard_ngo @ 2022-04-01 | +41 | 0 comments
Some thoughts on vegetarianism and veganism
by richard_ngo @ 2022-02-14 | +192 | 0 comments
Examples of pure altruism towards future generations?
by richard_ngo @ 2022-01-26 | +16 | 0 comments
Ngo's view on alignment difficulty
by richard_ngo, EliezerYudkowsky @ 2021-12-14 | +19 | 0 comments
What are some success stories of grantmakers beating the wider EA community?
by richard_ngo @ 2021-12-07 | +51 | 0 comments
Ngo and Yudkowsky on AI capability gains
by richard_ngo, EliezerYudkowsky @ 2021-11-19 | +23 | 0 comments
Ngo and Yudkowsky on alignment difficulty
by richard_ngo, EliezerYudkowsky @ 2021-11-15 | +71 | 0 comments
Is there anyone working full-time on helping EAs address mental health problems?
by richard_ngo @ 2021-11-01 | +34 | 0 comments
AGI Safety Fundamentals curriculum and application
by richard_ngo @ 2021-10-20 | +123 | 0 comments
Suggested norms about financial aid for EAG(x)
by richard_ngo @ 2021-09-20 | +73 | 0 comments
What are your main reservations about identifying as an effective altruist?
by richard_ngo @ 2021-03-30 | +91 | 0 comments
Some thoughts on risks from narrow, non-agentic AI
by richard_ngo @ 2021-01-19 | +36 | 0 comments
My evaluations of different domains of Effective Altruism
by richard_ngo @ 2021-01-15 | +29 | 0 comments
Clarifying the core of Effective Altruism
by richard_ngo @ 2021-01-15 | +54 | 0 comments
Lessons from my time in Effective Altruism
by richard_ngo @ 2021-01-15 | +287 | 0 comments
Scope-sensitive ethics: capturing the core intuition motivating utilitarianism
by richard_ngo @ 2021-01-15 | +141 | 0 comments
What foundational science would help produce clean meat?
by richard_ngo @ 2020-11-13 | +32 | 0 comments
AGI safety from first principles
by richard_ngo @ 2020-10-21 | +77 | 0 comments
EA reading list: utilitarianism and consciousness
by richard_ngo @ 2020-08-07 | +17 | 0 comments
EA reading list: other reading lists
by richard_ngo @ 2020-08-04 | +17 | 0 comments
EA reading list: miscellaneous
by richard_ngo @ 2020-08-04 | +27 | 0 comments
EA reading list: futurism and transhumanism
by richard_ngo @ 2020-08-04 | +20 | 0 comments
EA reading list: Paul Christiano
by richard_ngo @ 2020-08-04 | +23 | 0 comments
EA reading list: global development and mental health
by richard_ngo @ 2020-08-03 | +17 | 0 comments
EA reading list: Scott Alexander
by richard_ngo @ 2020-08-03 | +40 | 0 comments
EA reading list: replaceability and discounting
by richard_ngo @ 2020-08-03 | +12 | 0 comments
EA reading list: longtermism and existential risks
by richard_ngo @ 2020-08-03 | +35 | 0 comments
EA reading list: suffering-focused ethics
by richard_ngo @ 2020-08-03 | +43 | 0 comments
EA reading list: EA motivations and psychology
by richard_ngo @ 2020-08-03 | +28 | 0 comments
EA reading list: cluelessness and epistemic modesty
by richard_ngo @ 2020-08-03 | +27 | 0 comments
EA reading list: population ethics, infinite ethics, anthropic ethics
by richard_ngo @ 2020-08-03 | +25 | 0 comments
EA reading list: moral uncertainty, moral cooperation, and values spreading
by richard_ngo @ 2020-08-03 | +14 | 0 comments
richard_ngo's Quick takes
by richard_ngo @ 2020-06-13 | +6 | 0 comments
What are the key ongoing debates in EA?
by richard_ngo @ 2020-03-08 | +74 | 0 comments
Characterising utopia
by richard_ngo @ 2020-01-02 | +50 | 0 comments
Technical AGI safety research outside AI
by richard_ngo @ 2019-10-18 | +91 | 0 comments
Does any thorough discussion of moral parliaments exist?
by richard_ngo @ 2019-09-06 | +36 | 0 comments
How much EA analysis of AI safety as a cause area exists?
by richard_ngo @ 2019-09-06 | +94 | 0 comments
How do most utilitarians feel about "replacement" thought experiments?
by richard_ngo @ 2019-09-06 | +34 | 0 comments
Why has poverty worldwide fallen so little in recent decades outside China?
by richard_ngo @ 2019-08-07 | +24 | 0 comments
Which scientific discovery was most ahead of its time?
by richard_ngo @ 2019-05-16 | +34 | 0 comments
Why doesn't the EA forum have curated posts or sequences?
by richard_ngo @ 2019-03-21 | +35 | 0 comments
The career and the community
by richard_ngo @ 2019-03-21 | +93 | 0 comments
Arguments for moral indefinability
by richard_ngo @ 2019-02-08 | +34 | 0 comments
Disentangling arguments for the importance of AI safety
by richard_ngo @ 2019-01-23 | +63 | 0 comments
How democracy ends: a review and reevaluation
by richard_ngo @ 2018-11-24 | +27 | 0 comments
Some cruxes on impactful alternatives to AI policy work
by richard_ngo @ 2018-11-22 | +28 | 0 comments