EA Forum Podcast (All audio)

This is a link post.

This is a cross-post of our newly updated article with advice on working at frontier AI companies if you want to help with AI safety.

The original article was published in June 2023. We decided to update it in May 2024, as events in the intervening year caused us to be more concerned about working for frontier AI companies, and we also wanted to explain why we still thought it made sense for some people to take roles at AI companies. Our overall view is that “it's complicated”: working at a frontier AI company is sometimes a good idea, and sometimes a bad idea; it depends on the role and type of work, the company, and your individual case.

The new article tries to more clearly lay out the case in favour and against working at frontier AI companies, give tips for mitigating the downsides [...]

---

Outline:

(01:00) Summary

(01:31) Pros

(01:46) Cons

(02:05) Recommendation: it's complicated

(02:35) Review status: Based on an in-depth investigation

(03:18) Introduction

(04:00) Why might it be high impact to work for a frontier AI company?

(04:06) Some roles at these companies might be among the best for reducing risks

(06:25) A frontier AI company could be a huge force for good

(10:21) It could be very good career capital (though there may also be career capital downsides)

(14:48) Whats the case against working at a frontier AI company?

(14:53) You might increase the risk of an AI-related catastrophe

(22:14) There are great alternatives that lack many of the downsides

(23:14) Things to consider for your particular case

(23:49) There are very different kinds of roles

(24:47) Some companies are probably much more responsible than others

(29:29) It matters who you are

(30:36) How can you reduce the downsides of working at a frontier AI company?

(32:56) Where might you work instead?

(35:04) Explore jobs

(35:16) Learn more about working at AI companies

(36:13) Acknowledgements

The original text contained 9 footnotes which were omitted from this narration.

---

First published:

August 30th, 2024

Source:

https://forum.effectivealtruism.org/posts/RF3sKfnz6osxnvHj6/should-you-work-at-a-frontier-ai-company

---

Narrated by TYPE III AUDIO.

We just published an interview: Meghan Barrett on challenging our assumptions about insects. Listen on Spotify, watch on Youtube, or click through for other audio options, the transcript, and related links. Below are the episode summary and some key excerpts.

Episode summary

This is a group of animals I think people are particularly unfamiliar with. They are especially poorly covered in our science curriculum; they are especially poorly understood, because people don’t spend as much time learning about them at museums; and they’re just harder to spend time with in a lot of ways, I think, for people.

So people have pets that are vertebrates that they take care of across the taxonomic groups, and people get familiar with those from going to zoos and watching their behaviours there, and watching nature documentaries and more. But I think the insects are still really underappreciated, and that means that our [...]

---

Outline:

(00:28) Episode summary

(02:10) Highlights

(02:13) Size diversity

(05:32) Offspring, parental investment, and lifespan

(08:49) Headless cockroaches

(11:13) Is self-protective behaviour a reflex?

(14:29) If insects feel pain, is it mild or severe?

(19:40) Evolutionary perspective on insect sentience

(23:39) How likely is insect sentience?

---

First published:

August 29th, 2024

Source:

https://forum.effectivealtruism.org/posts/d8snuJrSnkCKb7sDv/198-challenging-our-assumptions-about-insects-meghan-barrett

---

Narrated by TYPE III AUDIO.

(Yes, yet another funding circle. Thank Ambitious Impact.)

I’m excited to announce the launch of the Strategic Animal Funding Circle, a new group of donors looking to support cost-effective and high-impact farmed animal welfare nonprofits during a critical growth phase where targeted funding can have an immense impact.

We’ve just launched our first Request For Proposals which you can see in this document, as well as being outlined below.

Apply here by September 20th to be considered for our first funding round. We aim for applicants to hear back on a decision by early November.

If there are any donors (either currently giving or willing to give upwards of $100-250k to farmed animals per year) interested in joining, feel free to email me at jozden[at]mobius.life. We expect the funding circle will expose donors to more high-impact opportunities, create the space for important discussions and reduce vetting inefficiencies.

[...]

---

Outline:

(01:04) Request for Proposals

(01:08) About this Funding Opportunity

(01:39) Eligibility Criteria:

(02:30) Selection Criteria: What Makes a Competitive Application?

(03:52) How to Apply:

(04:06) Future Rounds:

(04:16) About the Strategic Animal Funding Circle:

---

First published:

August 29th, 2024

Source:

https://forum.effectivealtruism.org/posts/cJ4jGs22CSA2A9SBo/announcing-the-strategic-animal-funding-circle

---

Narrated by TYPE III AUDIO.

Audio note: this article contains 119 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description.

Note: this has been in my drafts for a long time, and I just decided to let it go without getting too hung up on details, so this is much rougher than it should be.

Alexander Berger: ...the central idea of worldview diversification is that the internal logic of a lot of these causes might be really compelling and a little bit totalizing, and you might want to step back and say, “Okay, I’m not ready to go all in on that internal logic.” So one example would be just comparing farm animal welfare to human causes within the remit of global health and wellbeing. One perspective on farm animal welfare would say, “Okay, we’re going to [...]

---

Outline:

(05:27) Statistical decision theory

(09:30) Bayes risk minimization

(11:40) Minimax risk minimization

(15:12) Expected utility maximization

(18:59) Conclusion

(19:26) Appendix: deriving risk

---

First published:

August 23rd, 2024

Source:

https://forum.effectivealtruism.org/posts/wHaj9zpoeraQqBG9H/statistical-foundations-for-worldview-diversification

---

Narrated by TYPE III AUDIO.

Legal Impact for Chickens is hiring a Staff Attorney or Managing Attorney. We are prioritizing applications submitted by October 7.

About us:

Legal Impact for Chickens (LIC) is a 501(c)(3) litigation nonprofit. We work to protect farmed animals.

You may have seen our Costco shareholder derivative suit in The Washington Post, Fox Business, or CNN Business—or even on TikTok. Or perhaps you saw LIC recommended by Animal Charity Evaluators.

Now, we’re looking for our next hire—an entrepreneurial litigator to help fight for animals!

About you:

• 2+ years of litigation experience (for staff attorney)

• 6+ years of litigation experience (for managing attorney)

• Licensed and in good standing with the state bar where you live

• Excellent analytical, writing, and verbal-communication skills

• Zealous, creative, enthusiastic litigator

• Passion for helping farmed animals

• Interest in entering a startup nonprofit on the ground floor, and [...]

---

First published:

August 27th, 2024

Source:

https://forum.effectivealtruism.org/posts/tCrhQ94sqovr2sgKu/legal-impact-for-chickens-is-hiring-an-attorney

---

Narrated by TYPE III AUDIO.

This is a link post.

We have yet to see anyone describe a critical element of effective AI safety planning: a realistic model of the upcoming role the US government will play in controlling frontier AI.

The rapid development of AI will lead to increasing national security concerns, which will in turn pressure the US to progressively take action to control frontier AI development. This process has already begun,[1] and it will only escalate as frontier capabilities advance.

However, we argue that existing descriptions of nationalization[2] along the lines of a new Manhattan Project[3] are unrealistic and reductive. The state of the frontier AI industry — with more than $1 trillion[4] in private funding, tens of thousands of participants, and pervasive economic impacts — is unlike nuclear research or any previously nationalized industry. The traditional interpretation of nationalization, which entails bringing private assets under the ownership of a [...]

---

Outline:

(02:27) Part 1: What is Soft Nationalization?

(04:02) 1. Private US labs are currently the leading organizations pushing the frontier of AI development, and will be among the first to develop AI with transformative capabilities.

(05:04) 2. Advanced AI will have significant impacts on national security and the balance of global power.

(07:18) 3. A key priority for the US government is to ensure global military and technological superiority.

(08:57) 4. Hence, the US government will begin to exert greater control and influence over the shape, ownership, and direction of frontier AI labs in national security use-cases.

(09:51) Why Total Nationalization Is Not The Most Likely Model

(14:42) Upcoming Projects on Soft Nationalization

(15:48) 1. Describing Soft Nationalization

(16:49) 2. Conducting Further Scenario Research

(17:40) 3. Aligning AI Safety with Soft Nationalization

(18:39) Part 2: Policy Levers for Soft Nationalization

(20:05) Management and Governance Mechanisms

(20:22) Government Oversight

(21:33) Government Management

(22:45) Government Projects and Integrations

(24:04) Operational Control

(24:21) Development Limitations

(25:26) Customer Limitations

(26:43) Deployment / Use Limitations

(27:49) Compute Usage Limitations

(29:27) Security and Containment Measures

(29:41) Personnel Requirements

(31:02) Research and Information Controls

(32:24) Cybersecurity Requirements

(33:38) Containment Requirements

(34:36) Financial Ownership and Control

(34:53) Shareholding Scenarios

(36:08) Profit Regulation and Unique Tax Treatment

(37:11) Part 3: Scenarios Illustrating Soft Nationalization

(38:20) US “Brain Drain”

(40:23) Escalation of an AI Arms Race

(43:33) Nationalization of Bioweapon Technologies

(46:54) Conclusion

The original text contained 32 footnotes which were omitted from this narration.

The original text contained 4 images which were described by AI.

---

First published:

August 27th, 2024

Source:

https://forum.effectivealtruism.org/posts/47RH47AyLnHqCQRCD/soft-nationalization-how-the-us-government-will-control-ai

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

This is a link post.

Japan spent more than $19.6 billion on overseas development assistance (ODA) in 2023, making it the third largest single-country donor behind the US and Germany. Open Philanthropy's Global Aid Policy (GAP) team, which is devoted to increasing government aid and guiding it toward more cost-effective approaches, believes there may be opportunities to increase the impact of this aid through targeted advocacy efforts. They estimate that in Western nations like the UK, for every $1,000 spent on ODA, aid advocacy funders spend around $2.60 attempting to support and inform its allocation. Meanwhile, in Japan, advocacy spending is a mere $0.25 for the same amount — more than 10 times less. Accordingly, the GAP program has prioritized work in Japan. The following case study highlights one grantee helping to drive this work forward.

*****

One day in March 2023, in the district of Wayanad near India's southern [...]

---

First published:

August 27th, 2024

Source:

https://forum.effectivealtruism.org/posts/JDgGiAwH9tGQcLT6u/how-platinum-helps-draw-attention-to-japan-s-role-in-global

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

This is a link post.

This is a crosspost for The most basic rationality techniques are often neglected and Rationality and discipline by Stefan Schubert, published on 30 August and 15 September 2021.

The most basic rationality techniques are often neglected and Rationality and discipline

How much can we "debias" ourselves? What should we do to become more rational? When discussing those issues, people usually focus on sophisticated debiasing techniques (“pre-mortem”) and advanced concepts from epistemology and statistics. What's often forgotten is that we already have a bunch of very simple but effective techniques for improving our rationality, such as (cf. Grice's maxims):

“Don’t believe things for which you lack evidence. And don’t say such things in discussions.”

“Don’t make irrelevant personal attacks.”

“Don’t attack straw men."

“Define your terms clearly.”

“Make one point at a time.”

“Try not to be too emotional when thinking about heated issues.”

It seems [...]

---

Outline:

(00:22) The most basic rationality techniques are often neglected and Rationality and discipline

(03:09) Rationality and discipline

---

First published:

August 26th, 2024

Source:

https://forum.effectivealtruism.org/posts/YLXhmbjeszjeCzXrz/the-most-basic-rationality-techniques-are-often-neglected

---

Narrated by TYPE III AUDIO.

Since I started in my position of Community Building Grants (CBG) manager at CEA, a program focused on a subset of city and national EA groups, I noticed that not everybody has an understanding of what city and national groups are doing, and how they could be impactful.

With this post I would like to highlight a few examples of successful city and national groups (from the CBG program, as I am most familiar with these groups), hoping that this will shine more light on what these kinds of groups do, and how this might lead to impact[1].

How city and national groups produce value

In general, we think city and national EA groups can have impact through different theories of change[2]:

1. Supporting talent to work on top causes
2. Incubating and accelerating local/university groups and other EA projects
3. Building local infrastructure (such as operational support for [...]

---

Outline:

(00:38) How city and national groups produce value

(02:07) Success stories

The original text contained 2 footnotes which were omitted from this narration.

---

First published:

August 26th, 2024

Source:

https://forum.effectivealtruism.org/posts/hqsYvcZMBt6rwR4nr/examples-of-success-from-city-and-national-groups

---

Narrated by TYPE III AUDIO.

The basic idea

Aether will be a small group of talented early-career AI safety researchers with a shared research vision who work full-time with mentorship on their best effort at making AI go well. That research vision will broadly revolve around the alignment, control, and evaluation of LLM agents. There is a lot of latent talent in the AI safety space, and this group will hopefully serve as a way to convert some of that talent into directly impactful work and great career capital.

Get involved!

1. Submit a short expression of interest here by Fri, Aug 23rd at 11:59pm PT if you would like to contribute to the group as a full-time in-person researcher, part-time / remote collaborator, or advisor. (Note: Short turnaround time!)
2. Apply to join the group here by Sat, Aug 31st at 11:59pm PT.
3. Get in touch with Rohan at [email protected] with any questions.

Who are we?

Team [...]

---

Outline:

(00:05) The basic idea

(00:38) Get involved!

(01:12) Who are we?

(01:15) Team members so far

(03:26) Advisors

(03:50) Research agenda

(05:50) Logistics

(06:56) Considerations

(07:00) Why you might want to join Aether:

(09:29) Why you might not want to join Aether:

(10:24) Sample of semi-concrete project ideas

---

First published:

August 21st, 2024

Source:

https://forum.effectivealtruism.org/posts/BEuJdpTPcyKYaD9X7/apply-to-aether-independent-llm-agent-safety-research-group

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.