Introduction

At AI-Plans.com, we are creating an accessible, centralized platform to discover and learn about the numerous alignment plans in existence. Our mission is to make the field of AI Alignment more transparent and accessible by providing a comprehensive compendium of alignment plans, along with criticisms against them.

As part of our effort to crowdsource knowledge and foster a critical, constructive discussion in the AI Alignment community, we are excited to announce the AI-Plans.com Critique-a-Thon, set to begin on the 1st of August and last for 10 days.

Proposal

We propose a prize fund of $500 to be awarded to the authors of the best critiques submitted during the Critique-a-Thon. Critiques will be judged based on the following criteria:

1. Accuracy: The criticism must correctly represent the alignment plan being critiqued. Misrepresentations would be deemed as unfair criticism.
2. Precision: Critiques must be precise and specific about the problem identified. Vague criticisms will be considered weaker than those providing an exact argument that could be assessed or refuted.
3. Communication: The criticism must clearly articulate its point. The critique should be formatted well, concise, and minimize the use of specialist language.
4. Evidence: Criticisms should be backed by logical reasoning and objective evidence, rather than speculative opinions.
5. Novelty: The criticism should raise new issues not already covered by others. Novel critiques will be considered more valuable than those rehashing known issues.

The judgments will be made by myself, members from our team(which includes an expert QA and Azai who has a strong background in mathematics), DragonGod (studying a Theoretical Computer Science Msc ), and a select group of alignment researchers.

Who is on your team and what's your track record on similar projects?

Our team includes Jonathan Ng, an independant alignment researcher, who will be taking a look at some critiques. Other members of the team include an expert QA with many years of experience and Azai, who has a strong background in mathematics. DragonGod, who is studying an Msc in Theoretical Computer Science will also be a judge for critiques. We also have a consultant who is CompTia certified, highly skilled in cybersecurity and red-teaming and a professor.
We have successfully launched AI-Plans.com in beta and have already added over 100 alignment plans to the site.
I myself, have helped get a start-up off the ground from nothing, going door to door- to having 3 branches, thousands of customers and schools requesting for internships. During the process I saw a lot of other start-ups, with much more qualified people fail completely and learnt what it takes to fail(overconfidence in the product, lack of outreach and market research, laziness, many things) and what it takes to succeed- determination and a sharp, user-focused mind.
I have been assisting Stake Out AI with narrative-building and proofreading and helping out at VAISU as well. I'm confident in my skill of breaking down the reasons an idea can and will fail and then finding ways to reach into it and extract something valuable.

Impact

The Critique-a-Thon not only fosters a vibrant discussion in the AI Alignment community but also accelerates the development of our platform by adding more plans and criticisms. It will contribute to the completion of Stage 1 of our project, making it easier for users to understand the existing plans and their common problems.

Budget

We have a Manifund for the prize fund here: https://manifund.org/projects/ai-planscom-critique-a-thon-300-prize-fund-proposal

The $500 prize fund will be distributed as follows:

1st place: $200

2nd place: $125

3rd place: $75

Honorable mention 1: $50

Honorable mention 2: $50

Conclusion

We believe this Critique-a-Thon will be an important step in developing our AI Alignment compendium and fostering a community of critical, constructive thinkers. We look forward to seeing the insightful critiques from our community members and advancing the field of AI Alignment together.

 

If you're interested in joining: https://discord.gg/zK6aREpy