It is standard form in EA to state one's welcomingness of feedback, both in a personal and professional capacity. Individuals and organisations alike often have many means by which you can deliver feedback, whether through anonymous forms or direct communication, and forum posts will often begin or end with:

"I'm open to feedback..."
"I'm looking for feedback of the following nature..."
"I'm very full because I ate feedback for breakfast, but there's always room for more..."
And so on.

I'm now wondering: what happens if you write, "I am not open to feedback". Literally, is that even allowed? I've never seen it done. I'm concerned to see such heterogeneous thinking on the topic and I find it alarming that a community which espouses openness would be so closed off to non-openness.

How is it that not a single person in this intellectual, professional, personal community, or [...]

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

It's time for safety conscious researchers to leave Anthropic

This is a short post, due to an unfortunate lack of time (in more ways than one).

I think it's pretty clear that AGI might come about rather (or indeed, very) soon. I don’t need to rehash on this forum why this might be amongst the most transformative events in history, and importantly, the catastrophic implications if this goes wrong. Whilst this community has often focused heavily on avoiding either misuse by ‘bad actors’ (often perceived to be terrorist groups) or misalignment risk, the risks of conflict or huge power concentration, as well as systemic risks cannot be ignored. Also, as the recent debate week showed, even supposedly ‘good’ actors might lock in their values, and if these are sufficiently different to the ‘true’ values, eg they fail to adequately value digital minds, for example, this may be [...]

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

Epistemic status - statistically verified.

I'm writing this post to draw peoples' attention to a new cause area proposal - haircuts for alignment researchers.

Aside from the obvious benefits implied by the graph (i.e. haircuts having the potential to directly improve organizational stability), this would represent possibly the only pre-singularity opportunity we'll have to found an org named "Clippy".

I await further investment.

---

First published:

Source:

---

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.

Misaligned AI systems, which have a tendency to use their capabilities in ways that conflict with the intentions of both developers and users, could cause significant societal harm. Identifying them is seen as increasingly important to inform development and deployment decisions and design mitigation measures. There are concerns, however, that this will prove challenging. For example, misaligned AIs may only reveal harmful behaviors in rare circumstances, or perceive detection attempts as threatening and deploy countermeasures – including deception and sandbagging – to evade them.

For these reasons, developing a range of efforts to detect misaligned behavior, including power-seeking, deception, and sandbagging, among other capabilities, have been proposed. One important indicator, though, has been hiding in plain sight for years. In this post, we identify an underappreciated method that may be both necessary and sufficient to identify misaligned AIs: whether or not they've turned red, i.e. gone rouge.

In [...]

---

Outline:

(01:43) Historical Evidence for Rouge AI

(02:59) Recent Empirical Work

(05:18) Potential Countermeasure

(05:22) The EYES Eval

(06:27) EYES Eval Demonstration

(07:40) Future Research Directions

(08:42) Conclusion

---

First published:

Source:

---

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.

We at Pivotal™ are thrilled to announce that we have successfully trademarked the terms "pivotal," "to pivot," and "a pivot" (see our official trademark certificate). We've long tolerated the unauthorised and, frankly, inflationary use of these terms, but the situation has reached a tipping point. So we're forced to take this pivotal™ action.

What does this mean for you?

• Moving forward, any post on the EA Forum containing the aforementioned trademarked terms will be automatically tagged with our EA forum tag by our proprietary AI system.[1]

• Furthermore, our system will automatically detect and gently correct unauthorized synonyms such as 'crucial', 'important', or 'critical', replacing them with the legally compliant term 'pivotal™'.
• At this stage, we have decided not to pursue legal actions against community members inadvertently infringing our trademark. Instead, they will simply be considered an automatic applicant to our upcoming research fellowships.

We appreciate your understanding [...]

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

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

Hi group organisers,

The current intro fellowship syllabus is getting on to be ~3 years old now, and many of you have remarked that it needs an update. As good stewards of EA, we have listened to your feedback and are pleased this April 1st to announce our proposed revamp!

• Confusion over name variations
• People don’t do the readings
• No immediate impact
• Weak bonds between participants
• Too cause-neutral

Confusion over name variations

The Introductory Fellowship is also known as Intro Fellowship, Arete Fellowship, EA Fellowship, EA Seminar Program, EA Seminar Programme, Intro to EA Program, Introductory Seminar Program. Way too many names, way too confusing! We will be shortening the new program simply to ‘the Fellowship’.

People don’t do the readings

We understand that it is common for some fellows to skip some readings. This creates a [...]

---

Outline:

(00:27) Problems with the current Intro Fellowship

(00:42) Our proposed solutions

(00:46) Confusion over name variations

(01:11) People don't do the readings

(01:32) No immediate impact

(02:07) Weak bonds between participants

(02:45) Too cause-neutral

(03:19) View our draft fellowship revamp here

---

First published:

Source:

---

Narrated by TYPE III AUDIO.

Happy April Fools’ Day! It's time to put your strategic thinking to the test in The EA University Groups Prisoner's Dilemma!

How It Works

If you’re a member or organiser of an EA university group (or the CEA University Groups Team), then you’re eligible to play. Your group faces one big decision: Cooperate or Defect?

• Every player will use this form to vote on whether their group should cooperate or defect.
• Your group's position will be decided by majority vote.
• Voting closes at midnight tonight.
• Results will be announced tomorrow.

The Prizes

The Grand Prize

• The coveted Golden Spoon Trophy, engraved with the words "HUNGRY FOR IMPACT"

Bonus Prizes

• A T-shirt that reads "i cooperated/ defected in the prisoner's dilemma and all i got was this lousy t-shirt"
• Socks embroidered with the EA logo
• An impact calculator (calculates your real life-time impact[1])
• Sheldon the [...]

---

Outline:

(00:19) How It Works

(00:53) The Prizes

(01:37) The Rules and Prize Conditions

(02:13) Will You Cooperate or Defect?

The original text contained 1 footnote which was omitted from this narration.

---

First published:

Source:

---

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.

Epistemic status: highly certain, or something

The Spending What We Must 💸11% pledge 

In short: Members pledge to spend at least 11% of their income on effectively increasing their own productivity.

This pledge is likely higher-impact for most people than the Giving What We Can 🔸10% Pledge, and we also think the name accurately reflects the non-supererogatory moral beliefs of many in the EA community.

Example

Charlie is a software engineer for the Centre for Effective Future Research. Since Charlie has taken the SWWM 💸11% pledge, rather than splurge on a vacation, they decide to buy an expensive noise-canceling headset before their next EAG, allowing them to get slightly more sleep and have 104 one-on-one meetings instead of just 101. In one of the extra three meetings, they chat with Diana, who is starting an AI-for-worrying-about-AI company, and decide to become a cofounder. The company becomes wildly successful, and [...]

---

Outline:

(00:15) The Spending What We Must 💸11% pledge

(00:39) Example

(01:26) The 💸💸💸 Badge

(01:55) FAQ

(01:58) Is the pledge legally binding?

(02:08) What do you mean by effectively increasing productivity?

(02:33) Im an AI system. Can I take the 💸11% pledge?

(03:23) Why is the 💸11% pledge 3x more effective than the 🔸10% pledge?

---

First published:

Source:

---

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.

Epistemic status: highly certain, or something

The Spending What We Must 💸11% pledge 

In short: Members pledge to spend at least 11% of their income on effectively increasing their own productivity.

This pledge is likely higher-impact for most people than the Giving What We Can 🔸10% Pledge, and we also think the name accurately reflects the non-supererogatory moral beliefs of many in the EA community.

Example

Charlie is a software engineer for the Centre for Effective Future Research. Since Charlie has taken the SWWM 💸11% pledge, rather than splurge on a vacation, they decide to buy an expensive noise-canceling headset before their next EAG, allowing them to get slightly more sleep and have 104 one-on-one meetings instead of just 101. In one of the extra three meetings, they chat with Diana, who is starting an AI-for-worrying-about-AI company and decides to become a cofounder. The company becomes wildly successful, and [...]

---

Outline:

(00:14) The Spending What We Must 💸11% pledge

(00:39) Example

(01:25) The 💸💸💸 Badge

(01:54) FAQ

(01:57) Is the pledge legally binding?

(02:08) What do you mean by effectively increasing productivity?

(02:38) Im an AI system. Can I take the 💸11% pledge?

(03:29) Why is the 💸11% pledge 3x more effective than the 🔸10% pledge?

---

First published:

Source:

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.

TL;DR: This is a reply to Launching Screwworm-Free Future – Funding and Support Request — EA Forum, Screwworm Free Future is hiring for a Director, and Animal ASK's report on Brazil - with a summary of challenges for NWS eradication in South America, such as the existence of large populations of flies (well-adapted to the environment) and relevant information gaps.

Many drafts of this doc were shared and discussed with SFF project team members (as I was myself part of it until recently). Their feedback was remarkably helpful; this text would be way worse without them, and I am grateful for this – especially to Diego, Carol, and Richard Parr. We even considered posting as a report authored by the team, but our schedules conflicted a lot, and we couldn’t agree on a final version and deadline. Thus, except for my co-author Fernando Moreno (who attended 5 meetings [...]

---

Outline:

(01:35) Introduction

(03:50) Straight to the point:

(07:20) Possible institutional challenges

(10:00) Natural and geographical challenges

(12:12) In summary

---

First published:

Source:

---

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.