Lab Leaks, Black Holes, and Eggs: Epistemic Case Study Competition

FLF is running a competition to find the best workflows and methodologies for using AI to produce reliable, trustworthy knowledge bases, grounded in real-world cases. We’re open-minded on the types of submissions we receive and on how they address the problem. We’ve set aside approximately $200k for prizes. Winning submissions may receive a prize from $5k-$50k and if submissions warrant, multiple $50k prizes are possible. Winners may be offered opportunities for further funded work. You can express interest right away to receive commentary, information, and updates — whether you’d like to participate or are just interested in the outcomes of the competition. The heights of human epistemic investigation are impressive and valuable, but rare and difficult to reach — see our abridged collection of strong examples.[1] The limiting factor is rarely exquisite insight (though this helps!), and more often diligence, a curious and open mindset, and the time and effort needed to do the thorough work investigating background on a topic: activities AI is well placed to assist with. Existing AI-assisted knowledge base work demonstrates real pieces of this — agent memory (e.g., Claude Code's memory and skills), LLM-curated personal wikis (Karpathy's perhaps the highest-profile), and deep-research tools. But these mostly produce single-user artifacts tuned to one investigator's context, not the kind that travel, combine, or survive (especially adversarial) scrutiny. We’re particularly excited by the compounding potential — if structured analyses[2] become reusable, refineable artifacts, every serious investigation enables future work, on the same or related topics, and by the same or different people, to reach further from a more solid epistemic foundation. Who knows, you might even solve debate! This competition provides three challenging case studies — with deliberately varied challenge profiles — and invites you to produce tooling and techniques to help people navigate them. First, the debated and impactful question of COVID-19 origins. Second, the risk that the Large Hadron Collider (LHC) creates synthetic black holes (perhaps destroying the Earth). Third, the health impact of eggs (as a human food source). The tooling should be general: we’ll judge against these and also other difficult case studies. What we're looking for We want to see workflows and methodologies using AI that advance the state of the art in carrying out epistemic investigations and producing compounding knowledge bases. We aren’t asking you to build an entire, robust, fully-featured system. Instead, we’re excited by any submission that advances the state-of-the-art on a component.[3] We’ve found it useful to think of these investigations as being split into several different layers: ingestion, structure, and assessment (more here). When stacked together and operating in concert, they’d create useful trusted artifacts. Something like a superior deep research, generating and interacting with a structured knowledge base, aimed at the truly epistemically discerning consumer. Below are a set of ideas for potential desiderata for a workflow. We’d expect most submissions to not be solely focused on a single layer, as we’re guessing for something to be useful it needs to work across the layers — but some discipline in separating these responsibilities may be useful for producing interoperable, shareable, compounding benefits. Ingestion How do you take a messy, multi-source evidence base and turn it into something structured enough to reason over? Extract and attribute claims to specific sources, with provenance metadata (who said what, when, in what context). Identify when the same claim appears across multiple sources in different forms. Search for resources with bearing on topics and subtopics at hand. Capture useful metadata tags. For example relating sources and claims to topics and other sources (toward structure) or about methodologies, deference, and assumptions (toward assessment). Structure How do you document the relationships between claims so that the full shape of the argument becomes navigable? Resolve the inference structure: which claims and evidence are offered as support for which other claims. Represent the discourse structure: where people are addressing different sub-questions and perhaps how they are tracking those relating to an overall inquiry — there may be explicit, and sometimes implicit, differences of emphasis. Capture relationships regarding "similar but not identical" claims. These could be different ways of framing conditions or caveats to statements, or different estimates of uncertainty for quantities or propositions. Track how the structure evolves over time. Assessment How do you evaluate what to actually believe, or what to look at next, given everything above? Identify rhetorical moves that carry more persuasive weight than evidential weight. Flag correlated evidence being treated as independent. Identify cruxes