Browse Comments — Clean (de-noised)

Thank you, Interesting Medicine. This is where gut health gets really practical. Most of us focus only on what we eat, but our body also responds to how that food is prepared, broken down, and absorbed. Sometimes better digestion starts with a simple kitchen adjustment, not a more complicated routine.🙏

Very useful report. Thanks for the wonderful work.

This is a great insight. Thanks for sharing.

These people need to be investigated for intelectual property theft....

Is it just me or does the actual flight path look nothing like the red live?

Mouli, great perspective 👍

One question I keep coming back to: As AI systems become increasingly agentic and distributed, the challenge may no longer be intelligence itself, but the stability of intelligence under continuous adaptation. How do we preserve learning while preventing the propagation of drift across agents, sessions, and time? It feels like many of the next-generation AI architectures will need explicit mechanisms for adaptation, isolation, recovery, and consensus—not just more capable models.

This is brilliant research on linguistic bias. Would love to exchange notes on this!

Jing-er? 😆

I see cannibalism.. Or whatever you call it in plants 😉. Interesting facts💫

Great insight! Thanks for sharing this perspective.

Thanks for the experiment and the insights My own add: Regional differences are real, yet many business leaders still call for one-size-fits-all approaches where solution originally developed for US and Europe would work well in Asia

Good insight.

Aaron (Ari) Bornstein Anchor the location explicitly in the system prompt based on the user's profile, not their language. The model already knows how to apply the right norms, and it just needs the right context.

Sachin Yerrawar This is a great example. The fact that you saw the same behavior with Claude on lab reports suggests this is a cross-model pattern, not a Gemini-specific quirk.

Bill Faruki Interesting approach. The translate-first pipeline would eliminate the language-to-location inference, but it introduces a different tradeoff: you lose cultural context that might actually be relevant. A Japanese patient describing symptoms with culturally specific framing (e.g., hesitancy, understatement) might get flattened in translation. The cleaner fix might be to keep the native language but anchor the location explicitly in the system prompt. That way you get both cultural sensitivity and the correct care pathway.

This post is packed with wisdom.

The expat case is the most alarming part, a Hindi speaker in San Francisco silently receiving Mumbai-anchored triage logic purely based on language. Language ≠ location, and in healthcare that gap can have real consequences.

This is so cool. I would never have thought of drawing a red line to instruct where things should go. Thanks for the tip.

Open-sourcing the dataset, python code, and README details here: