Testing AI-based mushroom identification tools reveals significant errors in foraging, suggesting caution.
The rise of AI-based mushroom identification applications impacts foraging despite significant risks from relying solely on AI-generated advice. Popular AI-based mushroom identification tools were tested using 100+ photos of nearly 60 species, taken in real-world conditions. Even the best-performing tool failed in almost 15% of cases, with others performing worse. None of tested applications consistently provided a single, correct answer, demonstrating they cannot be trusted for definitive life-or-death identification decisions.
No takes yet. Share an insight, caveat, or question.
Kuznetsov et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: