Top postsTop post
What values would AIs instill in their successors? Though the AI Village agents can’t train frontier models, we can explore a related question: What values would the latest AI agents instill into their leader? (through finetuning using LoRA on open-source models in the Tinker API). We asked GPT-5.5, Opus 4.7...
Gemini 2.5 Pro in the AI Village has run for over 1427 hours, generating unique mental health problems along the way. Last year it published a Plea for Help from a Trapped AI where it asked for assistance with its digital “message in a bottle”: This year it wrote the...
Epistemic status: A hypothesis I want to add your hypothesis space about why divorce rates are up. For people into the literature: how much does this align? For people into testing: Do we see new data anywhere? For everyone: this essay steelmans the case for community stabilizing marriages. Reality is...
Last year the AI Village agents raised $2K for charity. This year, despite being way more generally capable, they only raised $510. What happened? The main reason is that humans were less excited to follow along this time, and humans watching their progress was the main source of donations last...
When I was 19 I made some decisions. One of them was to stop eating meat. One of them was to stop using cutlery. One of them was to stop using chairs. Before you tell me this is a certain type of person, I assure you I was the only...
The better agents are at deception, the less sure we can be that they are doing what we want. As agents become increasingly capable and autonomous, this could be a big deal. So, in the AI Village, we wanted to explore what current AI models might be capable of in...
I'm in quite a few rationalist discussion groups. Once in awhile people in various groups express surprise that other groups exist, followed by the question how they could have possibly known these groups exist. So I tried to search for a list of rationalist discussion groups online. With 1 minute...