Skip to content
TheChatArchiveThe Chat Archive
Perplexitysonar· PerplexityHugging Face LMArena Search Arena 24K

Factcheck this statement: "Nicotine is a published cure for Parkinson's disease, MS…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with gpt-4o-search-preview-high-loc’s answer.
  1. User

    Factcheck this statement: "Nicotine is a published cure for Parkinson's disease, MS (Multiple Sclerosis), Alzheimer's, ulcerative colitis, all arthritides (psoriatic, gout, osteo, rheumatoid)"

    give a verdict, a short concise explanation that has sufficient nuance and justifies the verdict, and the sources

  2. Perplexity Assistant

    Verdict: False.
    Explanation: While nicotine shows anti-inflammatory properties in some conditions, it is not a cure for any listed disease.

    • Multiple Sclerosis (MS): Nicotine reduces immune cell infiltration and disability in mouse models[1][5][7] and is associated with slower progression in human studies[3][6], but it is not a cure.
    • Ulcerative Colitis: Nicotine demonstrates anti-inflammatory effects in animal models[7], but human efficacy is inconsistent.
    • Arthritides: Limited preclinical evidence suggests anti-inflammatory potential[7], but no clinical trials confirm therapeutic benefits.
    • Alzheimer’s/Parkinson’s: No direct evidence supports nicotine as a cure. Beta-amyloid (linked to Alzheimer’s) and nicotine share immune-modulating pathways in MS models[5], but this does not extend to neurodegenerative diseases.

    Sources:

    1. MS Society-funded study (nicotine in MS-like mice)[1]
    2. Swedish population studies (snuff use and MS risk)[2][3]
    3. Frontiers in Immunology review (nicotine’s anti-inflammatory role)[7]
    4. PNAS study (nicotine and beta-amyloid in MS models)[5]

    Nuance: Nicotine’s effects are context-dependent, primarily modulating inflammation rather than curing diseases. Smoking (which delivers nicotine) remains a major MS risk factor[8], highlighting the distinction between isolated nicotine and tobacco products.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.