AI should help researchers think deeper, not think less — Agent Bayes Blog<br>Blog The wrong question is whether AI can replace researchers. The useful question is whether it can help a researcher stay with a hard problem long enough to understand it.<br>That distinction sounds philosophical until you start designing the tool. Then it becomes a product requirement, which is the least romantic form a philosophy can take.<br>If the goal is replacement, the interface tends toward a button that produces an answer. If the goal is augmentation, the interface has to preserve the parts of research that make knowledge defensible: sources, uncertainty, disagreement, history, revision, and the human decision about what matters.<br>This fork is being argued well beyond research software. Harvard Business Review recently made the case that companies choosing augmentation over automation may win in the long run. I think research is where the argument is easiest to settle.<br>We built Agent Bayes around the second idea, not as a line in a manifesto after the fact but at the requirements and design level. The product is not trying to make research feel like ordering a report from a model. It is trying to help a person build a structure they can inspect, challenge, and keep improving .<br>The scarce resource is not text, it is sustained attention<br>LLMs made text cheap. That is useful, but it also distorts the conversation around research tools.<br>Most serious research problems are not blocked because no one can produce another paragraph. They are blocked because the researcher has to hold too many partially connected things in mind (usually across forty Zotero tabs!) at once: which papers agree, which ones only appear to agree, which claims are strongly supported, which ones depend on definitions, where the evidence ends, and which open question is actually worth another week.<br>When you as a researcher have a deep understanding of a subject, you can see where everything fits. You can see the contradictions, the gaps, the historical context, and the methodological shortcomings. Only then you can come up with a novel interpretation, challenge a consensus, or propose a new experiment. That is the work that makes research worth doing.<br>It is not glamorous. It often happens between sessions with a tool, while walking, rereading a passage, sketching a structure, throwing away a neat idea because a source does not support it, or realizing that two literatures use the same word to mean different things.<br>AI can speed up the entry into that state. It can surface relevant passages, provide background when you enter a field, translate across terminology, identify likely gaps, and suggest angles you might have missed.<br>But it cannot do the human part for you. It cannot sit with a problem for days, months, or years. It cannot feel when a theory is too neat, recognize the social and historical texture behind an argument, or decide which distinction matters morally, methodologically, or interpretively. In fields like history, archaeology, anthropology, sociology, psychology, and political thought, that human layer is not decoration. It is part of the subject.<br>Mohamed Mannaa, recently described the strange loop that forms when reviewers use AI to draft their reports and authors use AI to draft the responses. The work still looks human-led, but the thinking has been quietly outsourced on both sides. His warning is the same as ours from the other direction: the danger is not that AI produces text, it is that the person stops doing the part that made the text worth producing.<br>On the other hand, the body of research literature is growing faster than any one person can read. Researchers find themselves in a situation where they must use AI to keep up, but they expose themselves to the risk of blindly trusting a model that does not understand the stakes.<br>The best research tools should therefore make the human researchers more capable, accelerating their ability to keep the evidence visible, the disagreements legible, and the gaps clear. They should make it easier to think deeper, not think less.<br>Quality beats quantity<br>A bad research assistant gives you more. More summaries, more bullets, more plausible claims, more citations to verify yourself later. Spitting out more text than the U.S. Treasury prints dollars.<br>A good one generates claims that are scoped by the evidence, and scored by confidence. It provides accurate provenance for every citation it uses, that you can inspect in context.<br>Recent work on citation hallucination and verification is moving in this direction. Papers such as HalluCiteChecker, SemanticCite, and audits of LLM citation behavior such as How LLMs Cite and Why It Matters all circle the same practical problem: generated academic text can sound finished before it is epistemically earned.<br>That is why "quality over quantity" cannot be a vague preference. In a research workspace, it has to become a set of constraints:<br>A claim should point to the passage...