So I've recently been working a lot on one core question: Given that there are so many awesome movements already, how can we strengthen them by interconnecting them? After all, the main "issue" I'm currently seeing is discoverability, i.e. that there are so many projects which continuously replicate what others have done before; projects with very similar messages, but mostly separate communities, infrastructures and identities. It's way too easy to get stuck in certain bubbles.

You can find a broad overview of my endeavors at https://hermesloom.org/overview (many of my ideas revolve around creating digital infrastructure for economic empowerment and democratizing philanthropy), but what's relevant for this post is what I published at https://ultimatecollaboration.org/.

What I want to build is not a new movement, but instead a sort of "meta movement", i.e. one that aggregates details about all other movements, initiatives, grassroots projects etc. in the world and serves the user exactly what they want to see. One of my main ideas is a newsletter aggregator, i.e. a service which receives all the newsletters from all the projects that embody what I called "holistic regenerative transformation" (HRT) on Ultimate Collaboration, then an LLM would turn the contents of each newsletter into structured data, focusing especially on physical events (i.e. extracting the exact place and date for each event). Then each user can set up what they want to receive (e.g. "all events in Berlin around social entrepreneurship" or "all events that are relevant for my studies in X", etc.), of course also expressed in natural language and interpreted through an LLM to do the semantic matching to the event descriptions. Eventually, this should have a big impact to solve the issue of discoverability of many amazing small and large changemaking projects, so that people don't have to dig through endless websites and newsletters anymore, but instead get all the suggestions for events to visit in a highly concise, actionable way.

At https://ultimatecollaboration.org/#proposed-improvements-for-this-page, I already collected ideas for a broader vision of this "Synergypedia", but as mentioned, I think the most effective first step would be crowdsourcing newsletter signups and then developing an LLM-based system which reads out each newsletter and turns its contents into structured data, especially events which the respective organization announces. Additionally, it would probably need to read out websites, but also that should be pretty easy nowadays with tools like Firecrawl.

This entire system should be fully open source, GPL-licensed, self-hostable and of course generally free of charge. The server costs should be minor and I'm continuously building connections to the global philanthropy scene, so that funding should not be an issue. My dream is to build an entire community around this of LLM experts, programmers and the users themselves who continuously make sure that this new service contains as many of the world's HRT-related initiatives as possible, in every language, both global and national, but especially also hyper-local projects.

Now my issue is, and that's why I'm reaching out to you and writing this post: I don't know where to start. In my job I'm a CTO, i.e. the technical director of my startup, so I absolutely love managing large software projects and I do have substantial programming knowledge, but from the very start, I want to create this project together with other enthusiastic people. Also, right now I simply don't have more time than maybe a couple of hours per week, and as I'm not an actual LLM expert myself, I'm not entirely sure how to tackle this challenge of turning messy newsletters into a structured format; though I have the strong gut feeling that nowadays, all the puzzle pieces to realize this already exist, we just need to assemble them.

So I need help with communicating this idea well, including its context (i.e. why this even makes sense), but in a way which makes people engaged and take co-ownership in this themselves instead of being passive/non-participatory and thinking that it would be only "my" project. And in any case, I'd love to work together more with people who also want to use their programming skills for interconnecting the common good and who also see developing modular, interoperable, federated open source software as their calling.

Of course, if you or someone you know wants to take on that idea completely, I'd be honored to give it away! Obviously I don't claim ownership of this project idea; I simply want it to exist, so that we can all use it to get propelled in our developments and to look beyond our usual bubbles.

And if you feel that that might be relevant, feel free to contact me at synergies@hermesloom.org!

Yours in unity
Julian

Comments1


Sorted by Click to highlight new comments since:

there are so many projects which continuously replicate what others have done before; projects with very similar messages, but mostly separate communities, infrastructures and identities.

Some examples would be useful.

[comment deleted]0
0
0
Curated and popular this week
 ·  · 16m read
 · 
At the last EAG Bay Area, I gave a workshop on navigating a difficult job market, which I repeated days ago at EAG London. A few people have asked for my notes and slides, so I’ve decided to share them here.  This is the slide deck I used.   Below is a low-effort loose transcript, minus the interactive bits (you can see these on the slides in the form of reflection and discussion prompts with a timer). In my opinion, some interactive elements were rushed because I stubbornly wanted to pack too much into the session. If you’re going to re-use them, I recommend you allow for more time than I did if you can (and if you can’t, I empathise with the struggle of making difficult trade-offs due to time constraints).  One of the benefits of written communication over spoken communication is that you can be very precise and comprehensive. I’m sorry that those benefits are wasted on this post. Ideally, I’d have turned my speaker notes from the session into a more nuanced written post that would include a hundred extra points that I wanted to make and caveats that I wanted to add. Unfortunately, I’m a busy person, and I’ve come to accept that such a post will never exist. So I’m sharing this instead as a MVP that I believe can still be valuable –certainly more valuable than nothing!  Introduction 80,000 Hours’ whole thing is asking: Have you considered using your career to have an impact? As an advisor, I now speak with lots of people who have indeed considered it and very much want it – they don't need persuading. What they need is help navigating a tough job market. I want to use this session to spread some messages I keep repeating in these calls and create common knowledge about the job landscape.  But first, a couple of caveats: 1. Oh my, I wonder if volunteering to run this session was a terrible idea. Giving advice to one person is difficult; giving advice to many people simultaneously is impossible. You all have different skill sets, are at different points in
 ·  · 47m read
 · 
Thank you to Arepo and Eli Lifland for looking over this article for errors.  I am sorry that this article is so long. Every time I thought I was done with it I ran into more issues with the model, and I wanted to be as thorough as I could. I’m not going to blame anyone for skimming parts of this article.  Note that the majority of this article was written before Eli’s updated model was released (the site was updated june 8th). His new model improves on some of my objections, but the majority still stand.   Introduction: AI 2027 is an article written by the “AI futures team”. The primary piece is a short story penned by Scott Alexander, depicting a month by month scenario of a near-future where AI becomes superintelligent in 2027,proceeding to automate the entire economy in only a year or two and then either kills us all or does not kill us all, depending on government policies.  What makes AI 2027 different from other similar short stories is that it is presented as a forecast based on rigorous modelling and data analysis from forecasting experts. It is accompanied by five appendices of “detailed research supporting these predictions” and a codebase for simulations. They state that “hundreds” of people reviewed the text, including AI expert Yoshua Bengio, although some of these reviewers only saw bits of it. The scenario in the short story is not the median forecast for any AI futures author, and none of the AI2027 authors actually believe that 2027 is the median year for a singularity to happen. But the argument they make is that 2027 is a plausible year, and they back it up with images of sophisticated looking modelling like the following: This combination of compelling short story and seemingly-rigorous research may have been the secret sauce that let the article to go viral and be treated as a serious project:To quote the authors themselves: It’s been a crazy few weeks here at the AI Futures Project. Almost a million people visited our webpage; 166,00
 ·  · 32m read
 · 
Authors: Joel McGuire (analysis, drafts) and Lily Ottinger (editing)  Formosa: Fulcrum of the Future? An invasion of Taiwan is uncomfortably likely and potentially catastrophic. We should research better ways to avoid it.   TLDR: I forecast that an invasion of Taiwan increases all the anthropogenic risks by ~1.5% (percentage points) of a catastrophe killing 10% or more of the population by 2100 (nuclear risk by 0.9%, AI + Biorisk by 0.6%). This would imply it constitutes a sizable share of the total catastrophic risk burden expected over the rest of this century by skilled and knowledgeable forecasters (8% of the total risk of 20% according to domain experts and 17% of the total risk of 9% according to superforecasters). I think this means that we should research ways to cost-effectively decrease the likelihood that China invades Taiwan. This could mean exploring the prospect of advocating that Taiwan increase its deterrence by investing in cheap but lethal weapons platforms like mines, first-person view drones, or signaling that mobilized reserves would resist an invasion. Disclaimer I read about and forecast on topics related to conflict as a hobby (4th out of 3,909 on the Metaculus Ukraine conflict forecasting competition, 73 out of 42,326 in general on Metaculus), but I claim no expertise on the topic. I probably spent something like ~40 hours on this over the course of a few months. Some of the numbers I use may be slightly outdated, but this is one of those things that if I kept fiddling with it I'd never publish it.  Acknowledgements: I heartily thank Lily Ottinger, Jeremy Garrison, Maggie Moss and my sister for providing valuable feedback on previous drafts. Part 0: Background The Chinese Civil War (1927–1949) ended with the victorious communists establishing the People's Republic of China (PRC) on the mainland. The defeated Kuomintang (KMT[1]) retreated to Taiwan in 1949 and formed the Republic of China (ROC). A dictatorship during the cold war, T