🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Does it still count as a turkey trot, if the wild turkeys are the ones trotting while you walk?

Adventures in the ☀️

Views of (and from) a cinder cone.

Waterfalls with some added water 🌧️

This 👇🏼, and: there are a lot of parallels to working with other people, in terms of providing the right context but not too much, directing as needed, etc.

Every question (more than 25!) that I’ve ever answered about exocrine pancreatic insufficiency (EPI/PEI), all in one post: bit.ly/EPI-FAQ (But if you find a question I haven’t answered, please ask it! And I’ll update the post.)

PERT Pilot users on iOS - I have a new feature to test if you want to get early access to it! ✨ (DM or email me for info on accessing the test version)

Prepare for wildfire smoke season today! Filtering the air in your home can improve your indoor air quality and reduce your exposure to smoke. A DIY box fan filter can be a cost-efficient filter option to improve indoor air quality in a single room or designated space. Learn

I haven't spotted this, but it's exactly correct: "context engineering" captures the fact that the previous responses from the model are a key part of the process, "prompt engineering" suggests that it's only the user prompts that matter

Escaped the grey today.

Forest wander day.

I think a dramatically underappreciated feature of LLMs is the value-add of scientists being able to read and engage with science outside where we have the most specialized expertise. This isn’t to suggest they are currently replacing experts but it puts a much greater range of

Summer turned on a week early in Seattle!

👀 a new feature in PERT Pilot is out today! 🎉 When you are choosing an enzyme dose for a new meal, you can see it in context of your past meals (and what you logged that work for you and didn’t work so well).

More data showing that we need to be thinking about improving feedback loops for humans and AI aspects of the HC system. Doctors and LLMs make mistakes. No good *systematic* path for patients to get mistakes fixed. (My experience illustrating this here: bit.ly/42bkqwG)