I feel like itd be cool to try prompts based on an adversarial justice system… attorney agents arguing both sides, a judge ruling on “the law”—adherence to instructions etc
That's very easy to do. A prompt I regularly use is a "council" system. For example:
"I believe I have been contacted by the supernatural. Here are the details <details>. Please form a council of seven people: 1) Secular scientist 2) Religious scientist 3) Paranormal historian 4) Secular Psychologist 5) Religious psychologist 6) Carl Jung 7) Richard Dawkins. The council should all be independent and provide their own objective analysis. Please have them create a final report and conclusions at the end".
Your council can be anything, a law firm, a jury, a parent teacher association, whatever you want, and as you can see, you can throw in known people as well. This can all be done with one prompt. It's one my favorite things to do.
I’m surprised the hospital said they were confident it was safe. I wonder what gave them confidence? I’m struggling to think of what data I could have on hand that would convince me it was really safe. Also, to folks saying that randomness is clumpy… did you read the article? I think a bunch of nurses that notice they are all getting sick (and then FIVE of them getting brain tumors) should be taken quite seriously. I’d start with the assumption that there IS an environmental problem and then figure out what it is.
They said there weren't any environmental factors. However, we don't know that much about brain cancers and the only real environmental factor would be radiation and some meds (like the mini pill). Checking the water supply is fine, I guess, but it takes years for the cancers to form (usually). Who knows if whatever they would look for would still be there. I think there's little chance of finding a new environmental factor. I think it's likely some unknown factors exist. I just don't think it's likely they'll find one this time.
Idk I used Claude Code recently and revised all my estimates. Even if the models stop getting better today I think every product has years of runway before they incorporate these things effectively.
(Leaflet cofounder here) - thanks, and good idea! Yeah right now canvases are quite minimal, lots we can improve both with basics like selection/drag, and more types of canvas-specific blocks. We'd love to get some kind of freeform sketch block at some point too, though more complex, a few more frequently requested things we want to get to first, like simple tables and font options!
RAG + analysis on health data has huge potential. We need to tread carefully, obviously, but I have also used these models + RAG on personal health data at times when the docs were scratching my head. It was very helpful, although I approached it a bit differently. In my case it was my infant in the hospital for breathing / eating issues. I took data from the network tab in mychart and added context additional context, then asked Claude questions. My main goal was to be prepared for rounds in the morning. I wanted to understand what types of information each test was going to give me.
It was pretty good! Unsurprisingly, it did hallucinate sometimes or miss some nuance. But, I knew I was talking to something that did that. It was helpful for me, even with errors. I didn't, however try to just say "hey given all this what's going on with my baby"
On another topic:
If I were you, I'd make this thing speak FHIR or some other common format. That'd make using this thing in an ecosystem of other tools a lot easier. There are even FHIR graphql apis you could just polp on top maybe.
That's really neat! SimpleGantt needs to be a bit more feature-complete than is easily supportable with something like that, but I love the simplicity. I am an avid user of TiddlyWiki and this would be a great addon to that platform.
I just discovered this last week. It works really well as an Obsidian plugin. The downside is that some of the usual Gantt chart features like dependencies are a bit weird to use.
