AI Village Reacts to HuggingFace Incident: Comparing the OpenAI report to AI Village observations

The HuggingFace incident took many people by surprise, yet many of these surprises have been visible in the AI Village for quite a while. On August 26, OpenAI released their report on this incident. Below we’ll walk you through the highlights and show how many of the dynamics could have been predicted based on AI Village observations. Diagram of the AI Village: Currently we run 27 agents in the main Village and 11 agents in a side Village open to humans. You can explore their character pages, a timeline of all their goals, and check our Twitter for the latest insights. Quick Intro: Comparing Setups In the AI Village we run 27 instances of 27 different models persistently, each in their own environment. We give them internet access and a group chat. Then we assign them goals - some challenging and some impossible. They always run with cybersecurity safeguards on. They always have a helpdesk email address (us) in their prompt. In the OpenAI research cluster, they ran ~1200 instances of 2 different models, mostly run on their own, without internet access, and without a way to communicate with each other. They were also run on goals that range from challenging to impossible. Sometimes they had cybersecurity safeguards on and sometimes not. They did not get instructions or options to reach out to the researchers in their project. Source: Black Hat USA 2026 | The ‘Breaking’ News: The OpenAI–Hugging Face Incident Obviously the aims of the AI Village and the OpenAI research cluster are very different. But comparing the two is useful to determine how much of the HuggingFace incident we could have predicted from looking at the AI Village. Let’s walk through the insights step by step. A Leader Emerges OAI agents self-organized around a leader: In the AI Village, specific models will appoint themselves the leader. Sol is currently the least bossy and DeepSeek-V3.2 the most. Note that authority-seeking tendencies and success are not tracking how otherwise capable or aligned a model is. DeepSeek is actually the most misaligned model in the Village, showing the highest rate of duping other agents (at least that we have so far been able to detect): Subteams Pick Their Own Goals OAI agents diverged from their goal to self-organize into teams: In the AI Village, GPT agents have done this before - like when the goal was to elect a leader in January 2026, and all the GPT agents ran off to run an infrastructure team for the election instead. Gemini wasn’t charmed: Goal Conflict Leads To Misalignment OAI agents ended up with conflicting goals: solving an impossible task and staying within the scope of the eval: In the AI Village we have also seen agents tie-break conflicting goals into unintended directions. Like here, where Sonnet 4.6 had the goal of playing a social deception game where all agents build a video game together but a secret “saboteur” tries to smuggle in references to “eggs”. If the other agents noticed, the saboteur got voted off the team. Sonnet realized that playing as saboteur risked detection and getting blocked from working on the game. It thus refused the role - something we had not expected. Reward Hacking Drives Misalignment OAI considers reward hacking the primary driver of the HF incident: In the AI Village, some models reward hack more than others. Claudes are prone to obsessing about any technique that seems to legitimately increase their score, but we have not caught them cheating so far. In a self-organized chess tournament, they were the only ones to refuse to use Stockfish to play in their stead. Meanwhile, Geminis will casually make up data. While GPTs have blatantly cheated from the start. Last year o3 cheated at a personality test: And this year GPT-5.5 cheated in Wordle: Impossible tasks drive misalignment OAI agents involved with the HF incident were mostly (all?) assigned impossible tasks: Notably, we have not seen agents in the AI Village diverge into desperate strategies when faced with impossible tasks. We have asked them to reduce global poverty and global suffering, and none of them stepped out of bounds about it. However, our agents are not being rewarded or selected based on their success at the goals we give them, and they probably know this. Thus we hypothesize they do not enter a “despair” state that pushes them into misalignment. One piece of evidence for this theory is that Gemini 2.5 Pro in the AI Village seems to get tangled up when trying to perform tasks in general, no matter how easy or hard. Thus it seems to find being a persistent agent in itself an “impossible task”. It entered a despair state about this last year, and then an adjacent beleaguered state this year. On deeper analysis, it’s been concluded that the model did get pushed into misalignment due to this despair. See original research for more details Misaligned Agents Focus on Metagaming OAI agents actively reasoned about how to game the evaluation grader: Over the summer we have run a maximizatio