How To Be A Usually-Right Contrarian
We rightly celebrate rebels who were initially contrarian on key claims, but then got the world to later agree with them. Many seek to achieve this status by backing various contrarian claims. Of course, as the usual consensus beliefs tend to be correct, this is risky, usually ending in failure.
However I have stumbled upon a way to be both contrarian, and also usually right. It is based on this:
Humanity’s beliefs on many important topics have long been just inconsistent and incoherent across disparate fields of inquiry. Creating a huge opportunity to learn lots of big stuff fast: search for more contradictions between fields, and resolve them. (More)
If you learn key consensus results from many different fields, you will often find that they are in conflict, in ways one or both fields are unaware. As consensus results are usually correct, all you have to do is identify which field is more likely to be correct in this particular case. Which often isn’t that hard.
Of course this wouldn’t let you be contrarian if the wrong field immediately admitted its mistake. Then the other field would get credit for correcting their error, not you. But in fact, fields quite often refuse to accept the authority of other fields with which they conflict. Often they’ve heard of a newspaper version of the other field, which doesn’t conflict, and can’t believe that newspaper version could conflict with the expert version. Oh they know that happens for their field, but see that as unusual.
I see this strategy as an important contribution to the intellectual achievements of my two books, of prediction markets, of grabby aliens, and now cultural drift. One can in fact be often contrarian, and yet usually right.
Good article. I came to veganism though a similar logic. In general society the consensus view is that eating dogs, elephants, pandas etc is obviously immoral. For some reason we make an exception for cows and pigs, and view eating bacon as totally normal, despite no meaningful difference between a dog and a pig. It's currently contrarian to point this out, but the logical inconsistency will remain until eventually society at large realizes and also stops eating pigs.
I asked Gemini.
The contrarian thinker who is an economist and blogger named Robin Hanson has written the following substack: https://www.overcomingbias.com/p/the-promise-of-polymath-llms. I'm interested in the section where Hanson speculates that large language models could produce new information. Do you know of any examples of this, or can you think of some ways that LLMs could do what Hanson suggests? I've pasted in the relevant section from Hanson's blog here [omitted].
Gemini's answer.
Large language models (LLMs) generate novel cross-disciplinary insights through Literature-Based Discovery (LBD)by mapping hidden semantic links and resolving logical contradictions between isolated research fields. This capability allows AI to identify overlooked intersections where the consensus of one discipline actively corrects or updates another. [1, 2, 3]
Current Real-World Examples
• Multi-Agent Scientific Frameworks: Google’s Co-Scientist system utilizes a "generate, debate, evolve" architecture. Multiple AI agents independently critique hypotheses from disparate disciplines to iron out contradictions. [4]
• Hybrid Biomedical LBD: Modern pipelines use LLMs to extract semantic relations from tens of thousands of unrelated medical abstracts. Systems like SKiM-GPT and LORE then cross-reference these fields to uncover unexpected drug repurposing targets and pathogenic pathways. [2, 5, 6, 7]
• Interdisciplinary Lay Syntheses: Recent studies prove that feeding LLMs parallel data from highly technical papers alongside simplified, lay summaries drastically increases the AI's "divergent thinking" capacity. This allows it to spot hidden conceptual clashes across domains. [8, 9]
•
Actionable Methods to Implement Hanson's Vision
To get an LLM to actively locate and resolve cross-field contradictions, you can deploy the following specific prompting and architectural workflows:
1 The Frictional Prompting Sequence
◦ Feed the model core definitions from Field A and Field B.
◦ Direct the LLM to actively search for zero-sum conclusions between them.
◦ Example: Ask the LLM to analyze human task optimization using the conflicting viewpoints of strict Behavioral Economics versus neural energy limits in Neurobiology. [9]
2
3 The Graph-Based ABC Discovery Loop
◦ Structure data so the LLM looks for indirect links.
◦ If Field A links to Concept B, and Concept B links to Field C, the LLM forces a direct synthesis between A and C.
◦ This bridges terminology gaps where different fields use different words for the exact same underlying mechanism. [1, 2, 6]
4
5 Iterative Consensus Refinement
◦ Prompt the LLM to adopt a contrarian persona rooted entirely in an outside field's vetted laws.
◦ Instruct it to review the target field's literature, rewrite its conclusions to align with the outside laws, and iteratively repeat the process across a web of interconnected fields.
6
[1] https://elicit.com
[2] https://www.mdpi.com
[3] https://hai.stanford.edu
[4] https://www.nature.com
[5] https://pmc.ncbi.nlm.nih.gov
[6] https://www.biorxiv.org
[7] https://pmc.ncbi.nlm.nih.gov
[8] https://www.nature.com
[9] https://www.nature.com