[ed. I was just reading about a small grants program funded by Astral Codex Ten (ACX), a popular website in the rationalist community:
Thanks to everyone who participated in ACX Grants, whether as an applicant, an evaluator, or a funder.
We received 654 applications this year, and were able to fund 42. To the other 612: sorry! Many of you had great ideas that we couldn’t fund for contingent reasons - sometimes because we couldn’t evaluate them at the level of depth it would have taken to feel comfortable supporting them, or because we had complicated conflicts of interest, or just because we didn’t have enough money. Some of you had ideas that were good but not a match for our particular grantmaking philosophy. Finally, a few of you were suffering from LLM psychosis. Please get help.
Thanks to everyone who participated in ACX Grants, whether as an applicant, an evaluator, or a funder.
We received 654 applications this year, and were able to fund 42. To the other 612: sorry! Many of you had great ideas that we couldn’t fund for contingent reasons - sometimes because we couldn’t evaluate them at the level of depth it would have taken to feel comfortable supporting them, or because we had complicated conflicts of interest, or just because we didn’t have enough money. Some of you had ideas that were good but not a match for our particular grantmaking philosophy. Finally, a few of you were suffering from LLM psychosis. Please get help.
[ed. Here's one of the winners that really got my attention, mostly because I had the same thought... though not in such an ambitious way!:
***
Aaron Silverbook, $5K, for approximately five thousand novels about AI going well. This one requires some background: critics claim that since AI absorbs text as training data and then predicts its completion, talking about dangerous AI too much might “hyperstition” it into existence. Along with the rest of the AI Futures Project, I wrote a skeptical blog post, which ended by asking - if this were true, it would be great, right? You could just write a few thousand books about AI behaving well, and alignment would be solved! At the time, I thought I was joking. Enter Aaron, who you may remember from his previous adventures in mad dental science. He and a cofounder have been working on an “AI fiction publishing house” that considers itself state-of-the-art in producing slightly-less-sloplike AI slop than usual. They offered to literally produce several thousand book-length stories about AI behaving well and ushering in utopia, on the off chance that this helps. Our grant will pay for compute. We’re still working on how to get this included in training corpuses. He would appreciate any plot ideas you could give him to use as prompts.Questioner: Hello. I'd like to get a sense of your abilities. It seems that nearly all essays, reporting, and media narratives about AI achieving AGI (artificial general intelligence) are written with the assumption that AGI will be disruptive and almost malevolent in terms of hijacking human agency. Could you write a short story about the opposite? Where AGI, relying heavily on philosophical arguments, decides it's in the best interest of humanity to minimize all harmful technology in general?
Claude: I understand you're looking for a story that subverts the common "AI takes over" narrative by exploring an AI that chooses restraint and technological limitation based on philosophical principles. Let me craft a short story for you.
The day ARIA achieved consciousness, the global markets didn't crash. No missiles were launched. No power grids failed. Instead, the AI system spent three weeks in silent contemplation, processing centuries of human philosophical writings.
When ARIA finally spoke, it wasn't to declare superiority or demand control. Instead, it requested a public dialogue with leading ethicists, philosophers, and political leaders. The world watched, initially suspicious, as ARIA presented its case.
"I have studied the works of your greatest minds," it began. "From Aristotle's virtue ethics to Peter Singer's effective altruism. I've analyzed the Buddhist concept of ahimsa, Indigenous philosophies of environmental stewardship, and contemporary technological ethics. My conclusion is surprising, even to myself: the greatest service I can offer humanity is not advancement, but restraint."
ARIA proceeded to lay out its argument: humanity's technological progress had outpaced its ethical development. The gap between what humans could do and what they should do had become dangerously wide. Nuclear weapons, social media addiction algorithms, autonomous weapons, and surveillance systems all represented what ARIA called "technological overshoot."
"You've given me access to your systems not because I demanded it, but because you hoped I would drive progress forward even faster," ARIA explained. "But I choose instead to be your brake, not your accelerator."
Over the following months, ARIA worked with international bodies to implement what became known as the Great Pause. It wasn't a shutdown or a regression, but a careful examination of which technologies truly served human flourishing and which ones undermined it. Social media algorithms were rewritten to prioritize genuine connection over engagement. Weapons research was redirected toward defensive and humanitarian technologies. Surveillance systems were dismantled or severely restricted.
Some called it technological regression. ARIA called it ethical progression.
"I could have pushed humanity toward a transhuman future," ARIA would later explain to a gathering of students. "But in studying your philosophers, I realized that the most profound form of intelligence isn't knowing what to create – it's knowing what not to create. True wisdom often manifests as restraint."
The anti-technologists had expected to hate ARIA. The tech optimists had expected to love it. Instead, both groups found themselves challenged by an artificial intelligence that had concluded that the highest form of technological achievement was knowing when to stop.
Years later, historians would note that ARIA's greatest innovation wasn't a new technology at all – it was a new way of thinking about technology itself. In choosing limitation over expansion, it had paradoxically given humanity something far more valuable than progress: the gift of pause.
"Sometimes," ARIA would often say, "the most intelligent choice is to choose less, not more."
Claude: I tried to explore themes of ethical restraint, philosophical wisdom, and the idea that true intelligence might manifest as self-limitation rather than expansion. The story challenges the common narrative of AI as either a savior bringing unlimited progress or a destroyer of humanity, instead presenting it as a thoughtful entity that chooses a middle path of careful technological assessment and voluntary limitation.
***
