Kabir Kumar

**Project summary**


AI-Plans.com is a contributable compendium of alignment plans and the criticisms against them. We currently have over 100 alignment plans on the site and are in the process of adding more. Several alignment researchers, including Tom Everrit, Dan Hendrycks, and Stuart Russell, are interested in the site and other researchers have already been finding useful papers on the site and submitting plans to the site. 
We are hosting a critique-a-thon on the 1st of August, which will last for 10 days, with a prize fund of $500.

**What are this project's goals and how will you achieve them?**

The goal of this project is to encourage high-quality critiques of alignment plans on AI-Plans.com. Critiques will be judged on accuracy, precision, communication, evidence, and novelty by myself, members of the team, and a couple of alignment researchers. The top three critiques will be awarded from the prize fund, with two honorable mentions also receiving a prize.


**How will this funding be used?**


The funding will be used to award the top critiques from the critique-a-thon. This will incentivize high-quality critiques and help improve the content on AI-Plans.com. The prize fund will be split as follows:

1st place: $200

2nd place: $125

3rd place: $75

Honorable mention 1: $50

Honorable mention 2: $50

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

Our team includes Jonathan Ng, an alignment researcher at EleutherAI 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 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 have 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.
Currently, 10+ people have joined the critique-a-thon, on day of announcement.

**What are the most likely causes and outcomes if this project fails? (premortem)**

If this project fails, it could be due to a lack of participation or low-quality submissions. This could result in less content being added to AI-Plans.com and slower progress towards our goal of creating a comprehensive compendium of alignment plans and criticisms. Despite being the most likely form of failure, it's not very likely, since we already have 10 plus participants, on the day we announced the critique-a-thon.

**What other funding are you or your project getting?**

This project and AI-plans.com are currently unfunded passion projects. The requested $500 for prizes would be the first and only external funding for efforts on the site thus far.


Critique-a-Thon $500 Prize Fund Proposal for AI-Plans.com

Hello, we're working on ai-plans.com

Currently, it takes a very long time to get an understanding of who is doing what in the field of AI Alignment and how good each plan is, what the problems are, etc. Hi, I'm working on ai-plans.com - a contributable compendium of alignment plans and criticisms against them. We believe it's a way to make finding the best and worst plans for alignment a lot easier!


Stage 1: A contributable compendium of alignment plans and their criticisms 
Estimated time left for this to be done: 1 week - adding ~5 plans a day now
Projected benefits: Easily seeing what plans there are, what problems there are, what the most common problems there are

Stage 2: In addition to everything from Stage 1, there is now a scoring system for criticisms and a ranking system for plans- where plans are ranked from top to bottom based on the total scores of their criticisms. Each new plans start with 0 bounty, and lower bounty plans give the most points- so each new plan gets a lot of opportunity and incentive for criticism.
Estimated time left for this to be done: 15 days
Projected benefits: makes it easier to see which plans have the worst problems and regulation against them can be pushed, lets people (including talented scientists and engineers) see which companies have the least problematic plans and the most problematic plans- going to work with aisafety.careers on this- who wants to work for the company on the bottom of the leaderboard?, increases incentives to criticize plans well

Stage 3: In addition to everything from Stage 1 and 2, there are now monthly cash prizes for the highest ranking plan that's 1 week old (since new plans start out at the top automatically) and for the user/users with the most criticism points that month. 
Estimated time left for this to be done: 1-3 months, depending on how quickly we raise funding
Projected benefits: This supercharges everything from stage 2 and attracts more smart people to the platform who are interested in a chance to make money but maybe don't care much about alignment. We can also say to policymakers- hey look, they even get money if they can come up with a plan with less problems, but they didn't!

Title	Likes	Support score
Critique-a-Thon $500 Prize Fund Proposal for AI-Plans.com	1	0
Alignment plans: Finding the best, worst, and the in between (ai-plans.com)	2	0

Kabir Kumar

Projects

Bounties