Hide table of contents

I've been recently considering thinking about AI Alignment as analogous to raising a child, and I want to get feedback on this idea. 

Specifically, aligning AI to human values feels like what happens when (for example, no offense intended) a mormon family raises their children to be mormon. I think of stories like Educated in which parents try really really hard to make their kid follow their religious values, and they sometimes fail. 

I think this view differs from other stories of alignment because it views an AGI as having its own goals other than just the ones we give it (maybe this is assuming inner misalignment by default?). This story feels very plausible because in our production of AGI, I think we will create agents that are morally valuable and have their own goals. The example of a mormon family feels relevant here because it seems morally dicey or wrong for parents to insist on their child's goals/values, it may likewise be dicey to write the utility function of another sentient being and center such a function on ourselves. Analogy may also be good because it shows just how hard alignment is. Analogy is lacking because children do not become super-intelligent.

Beyond feedback on this framing, I would also appreciate links to relevant things other people have written, thanks!

4

0
0

Reactions

0
0
New Answer
New Comment


1 Answers sorted by

There's a 5-minute video about this kind of thing from Rob Miles:

I guess the takeaway is something like:

Counter-framing: AI alignment [via ambitious value learning] as analogous to [figuring out how to build a system that won't destroy the world when you try and train it like] raising a child.

Comments1
Sorted by Click to highlight new comments since:

You're in good company. Tom Griffiths offers this analogy in Brian Christian's 'The Alignment Problem':

“Griffiths views parenthood as a kind of proof of concept for the alignment problem. The story of human civilisation, he notes, has always been about how to instill values in strange, alien, human-level intelligences who will inevitably inherit the reins of society from us - namely, our kids.”

Curated and popular this week
 ·  · 4m read
 · 
SUMMARY:  ALLFED is launching an emergency appeal on the EA Forum due to a serious funding shortfall. Without new support, ALLFED will be forced to cut half our budget in the coming months, drastically reducing our capacity to help build global food system resilience for catastrophic scenarios like nuclear winter, a severe pandemic, or infrastructure breakdown. ALLFED is seeking $800,000 over the course of 2025 to sustain its team, continue policy-relevant research, and move forward with pilot projects that could save lives in a catastrophe. As funding priorities shift toward AI safety, we believe resilient food solutions remain a highly cost-effective way to protect the future. If you’re able to support or share this appeal, please visit allfed.info/donate. Donate to ALLFED FULL ARTICLE: I (David Denkenberger) am writing alongside two of my team-mates, as ALLFED’s co-founder, to ask for your support. This is the first time in Alliance to Feed the Earth in Disaster’s (ALLFED’s) 8 year existence that we have reached out on the EA Forum with a direct funding appeal outside of Marginal Funding Week/our annual updates. I am doing so because ALLFED’s funding situation is serious, and because so much of ALLFED’s progress to date has been made possible through the support, feedback, and collaboration of the EA community.  Read our funding appeal At ALLFED, we are deeply grateful to all our supporters, including the Survival and Flourishing Fund, which has provided the majority of our funding for years. At the end of 2024, we learned we would be receiving far less support than expected due to a shift in SFF’s strategic priorities toward AI safety. Without additional funding, ALLFED will need to shrink. I believe the marginal cost effectiveness for improving the future and saving lives of resilience is competitive with AI Safety, even if timelines are short, because of potential AI-induced catastrophes. That is why we are asking people to donate to this emergency appeal
 ·  · 17m read
 · 
TL;DR Exactly one year after receiving our seed funding upon completion of the Charity Entrepreneurship program, we (Miri and Evan) look back on our first year of operations, discuss our plans for the future, and launch our fundraising for our Year 2 budget. Family Planning could be one of the most cost-effective public health interventions available. Reducing unintended pregnancies lowers maternal mortality, decreases rates of unsafe abortions, and reduces maternal morbidity. Increasing the interval between births lowers under-five mortality. Allowing women to control their reproductive health leads to improved education and a significant increase in their income. Many excellent organisations have laid out the case for Family Planning, most recently GiveWell.[1] In many low and middle income countries, many women who want to delay or prevent their next pregnancy can not access contraceptives due to poor supply chains and high costs. Access to Medicines Initiative (AMI) was incubated by Ambitious Impact’s Charity Entrepreneurship Incubation Program in 2024 with the goal of increasing the availability of contraceptives and other essential medicines.[2] The Problem Maternal mortality is a serious problem in Nigeria. Globally, almost 28.5% of all maternal deaths occur in Nigeria. This is driven by Nigeria’s staggeringly high maternal mortality rate of 1,047 deaths per 100,000 live births, the third highest in the world. To illustrate the magnitude, for the U.K., this number is 8 deaths per 100,000 live births.   While there are many contributing factors, 29% of pregnancies in Nigeria are unintended. 6 out of 10 women of reproductive age in Nigeria have an unmet need for contraception, and fulfilling these needs would likely prevent almost 11,000 maternal deaths per year. Additionally, the Guttmacher Institute estimates that every dollar spent on contraceptive services beyond the current level would reduce the cost of pregnancy-related and newborn care by three do
 ·  · 1m read
 · 
Need help planning your career? Probably Good’s 1-1 advising service is back! After refining our approach and expanding our capacity, we’re excited to once again offer personal advising sessions to help people figure out how to build careers that are good for them and for the world. Our advising is open to people at all career stages who want to have a positive impact across a range of cause areas—whether you're early in your career, looking to make a transition, or facing uncertainty about your next steps. Some applicants come in with specific plans they want feedback on, while others are just beginning to explore what impactful careers could look like for them. Either way, we aim to provide useful guidance tailored to your situation. Learn more about our advising program and apply here. Also, if you know someone who might benefit from an advising call, we’d really appreciate you passing this along. Looking forward to hearing from those interested. Feel free to get in touch if you have any questions. Finally, we wanted to say a big thank you to 80,000 Hours for their help! The input that they gave us, both now and earlier in the process, was instrumental in shaping what our advising program will look like, and we really appreciate their support.