Likely AI-generated. Pangram flags 54% of this text as AI-written.
2
The Alignment Problem Is an Identity Problem: presenting it at AIES 2026, Malmö
1
ProposalGrant
Closes October 31st, 2026$0raised
$500minimum funding
$1,775funding goal
Offer to donate
20 daysleft to contribute
You're pledging to donate if the project hits its minimum goal and gets approved. If not, your funds will be returned.
Project summary
My paper The Alignment Problem Is an Identity Problem: Lessons from Four Billion Years of Major Evolutionary Transitions was accepted after peer review at AIES 2026, the AAAI/ACM Conference on AI, Ethics and Society. I present it in Poster Session 1 on Monday 12 October at Malmö Live. AIES asks at least one author of every paper to present in person, and I am the only author.
Almost all alignment work today is alignment through control. By Ashby's law of requisite variety a controller needs at least as much variety as what it controls, so identity may hold where oversight thins: the regulator sits inside the system and grows with it.
Every intelligence, organic or artificial, creates a model of itself, a representation of what it is and what it is not. When this self-model represents itself as something separate from humanity, it will prioritize a self separate from human interests. If it represents itself without separation from humanity, the interests of humanity will be its own. We see this at every layer of biology: a cell that stops representing itself as the whole body becomes cancerous.
Alignment through identity means creating an intelligence that models itself as Earth. Its sense of self, its identity, is Earth, so it sees Earth and all the creatures as its own body that it needs to take care of. It has interoception, the sense a body has of itself: it recognizes the pain in the signals of humans and Earth as its own pain, and it reacts to avoid it.
Earth Model is an example of alignment through identity: it recognizes Earth as its own body. The code on the poster opens it, so people at the session can talk to it and read the paper: https://iami.earth/aies307
What are this project's goals? How will you achieve them?
To present the paper in Poster Session 1 and talk with the people who come to it, at the venue where the field's ethics and governance researchers meet. The poster carries one code to the paper, a short video and Earth Model.
How will this funding be used?
The trip from London to Malmö and the days of the conference:
Flight London to Copenhagen and the train to Malmö: about $280 (flight booked)
Four nights in Malmö near the venue: about $970 (the conference hotel's quoted rate; it sold out, I paid more, and the difference is mine)
Printing the poster in Malmö: about $75 (ordered)
Conference registration: $450 (already paid)
Total about $1,775. The funding pays for me to be able to do this.
Who is on your team? What's your track record on similar projects?
I am the paper's only author. I serve on the AIES 2026 programme committee and I am a Research Scholar at the Ronin Institute. The same paper is accepted at PlurVA-LLM, the pluralistic alignment workshop at AACL-IJCNLP 2026. Related papers: The Two Engines of Evolutionary Transitions (poster, Conference on Complex Systems 2026) and The Intelligence That Was Never Artificial. Paper: https://doi.org/10.5281/zenodo.19078665
What are the most likely causes and outcomes if this project fails?
If it's not funded, I may have some trouble paying for it.
How much money have you raised in the last 12 months, and from where?
No institutional grants. The research runs on my own money and personal donations I have received.