Because that's plainly not what they are always doing. And the aggressive, racist unprofessional, downright dangerous way ICE are going about things is simply shocking.
This is largely solved in biomedicine by funders (not journals) and regulatory bodies requiring that human subjects research data be stored with NIH.
I guess there may be a broader and less public-oriented set of funders in geology- and maybe there aren’t as many standardized data types as there are in the world of biology.
Are you seeing a benefit above doing this in the prompt / project structure?
Currently, I have Claude set up a directory with CLAUDE.md, a roadmap, a frequently used commands guide, detailed by-phase plans, and a session log with per-session insights and next steps.
After each phase is done, I have it update the documents and ask what could have been done to make the session easier—often the answer is clearer instructions, which eventually leads to topic-specific documents or a new Claude Skill.
(edit) These reflection tasks are spelled out in the CLAUDE.md and in the docs directory, so I don't have to type them. Each new session, I paste a guide for how Claude should access the information from the last session.
I keep the context concise by linking from claude.md to markdown files with the hardware architecture, the network architecture, the processing tech stack. Concise and specific. And a current project md.
I mix in the parts that are relevant.
I don't have a roadmap and session log though. Good idea.
Your workflow sounds solid - and honestly more disciplined than most. The difference I was going for: catching implicit corrections you don't consciously document.
So probably complementary to what you're doing, not a replacement. If you're already doing post-phase reviews, you might catch most of this anyway.
I totally understand that this is not really a small ask, but if you could put together some sort of example repo of this setup I and probably a lot of people with me would be most grateful! I don't mean with running code or anything, just the doc structure for Claude.
No problem! I recommend asking Claude for these sorts of things so they can better match your own processes.
----
New session:
## Prompt
Set up project documentation structure for this new project.
Create the following:
1. \*CLAUDE.md\* (project root) - Concise (<40 lines) entry point with:
- One-line hypothesis/goal
- "Start Here" pointing to docs/ROADMAP.md
- Quick Reference (key commands)
- Key Files table
- Documentation links
- "End of Session" protocol (append to docs/session_log.md)
2. \*docs/ROADMAP.md\* - Status dashboard:
- Current state table (what exists)
- Blockers table (with links to plans)
- Priority actions table (with links to plans)
- Success criteria (minimum + publishable)
3. \*docs/plans/\* directory with plan templates:
- Each plan: Priority, Status, Depends on, Problem, Goal, Steps, Success Criteria
- Name format: plan_descriptive_name.md (not numbered)
4. \*docs/runbook.md\* - Common operations:
- How to add new data sources
- How to run analysis
- How to run tests
5. \*docs/session_log.md\* - Work history:
- Template for session entries
- "Prior Sessions" section for context
6. \*docs/archive/\* - For completed/old docs
If this is a data pipeline project, also set up:
- SQLAlchemy + Pydantic architecture (see sqlalchemy_pydantic_template.zip)
- tests/ directory with pytest structure
- you can copy the file from ./generic_claude_project_src.zip to the current folder and unzip the copy. DO NOT modify the original file or try to move the original file
Keep all docs concise. Link between docs rather than duplicating.
---
## After Setup Checklist
- [ ] CLAUDE.md is <50 lines
- [ ] ROADMAP.md fits on one screen
- [ ] Each plan has clear success criteria
- [ ] runbook.md has actual commands (not placeholders)
- [ ] session_log.md has first entry from setup session
---
## python
use the py-PROJECT pyenv
ensure pyenv is installed
## Example Structure
project/
├── CLAUDE.md # Entry point (<50 lines)
├── docs/
│ ├── ROADMAP.md # Status + plan links
│ ├── runbook.md # Common operations
│ ├── session_log.md # Work history
│ ├── plans/
│ │ ├── plan_data_loading.md
│ │ ├── plan_analysis.md
│ │ └── plan_validation.md
│ └── archive/
│ └── plans/ # Old plans with date prefix
├── src/ or project_name_src/ # Code
└── tests/
└── test_*.py
## Session log example
## YYYY-MM-DD: Brief Title
\*Goal\*: What you aimed to do
**Done**: What was accomplished (be specific)
**Discovered**: Non-obvious findings about codebase/data/tools
**Decisions**: Choices made and brief rationale
**Deferred**: Work skipped and why (not just "next steps")
**Blockers**: Issues preventing progress (or "None")
The key shift: less about tasks completed, more about knowledge gained that isn't captured elsewhere.
Continuation prompt
Review the project state and tell me what to work on:
1. Read docs/ROADMAP.md
2. Read docs/session_log.md (last entry)
3. Read the highest-priority plan in docs/plans/
Then summarize:
- Last session (1 line)
- Current blockers
- Recommended next step
Ask if I'm ready to proceed.
The zip archive above is just a standard Python module with __init__ and hints at how I'd like things to be named.
This may exist already, but I'd like to find a way to query 'Supplementary Material' in biomedical research papers for genes / proteins or even biological processes.
As it is, the Supplementary Materials are inconsistently indexed so a lot of insight you might get from the last 15 years of genomics or proteomics work is invisible.
I imagine this approach could work, especially for Open Access data?
I wanted to find all cryoprotective agents that were tested at different temperatures, but it should be extandable to your problem too. Uses OpenAlex to traverse a citation graph and open access pdfs
It depends on what the true blood sugar value was: if someone were already at the high end of normal and a 'brittle diabetic', you can end up in 'diabetic ketoacidosis' for T1DM individuals or—less likely—'hyperosmolar hyperglycemic state' generally.
You can die on the order of hours to days not of high blood sugar per se, but of the low insulin causing diabetic ketoacidosis parent comment mentions.
It would be odd for a faulty sensor to cause an otherwise bad day into dka and death though. The sensor would need to be wildly off for hours and the user to not notice. Insulin delivery would need to be paused or greatly reduced for many hours. There are additional therapies like SGLT-2 that could make this more likely but they usually aren’t used with T1D precisely because they break the normally very strong correlation between inadequate insulin levels (leading to dka) and high blood glucose.
Even though I can’t think of an easy way for a false low(s) to turn into lethal DKA, that doesn’t mean it didn’t happen. Abbott sells a lot of CGMs. It could have been a contributing factor to several deaths even if the fault would almost always not be a significant issue.
> Sorry to be crass, but this type of argument is exactly why non-experts shouldn't be talking about topics
> I myself am not a doctor. I love to learn from my wife.
I suggest that you speak to your wife before correcting my unimpeachable explanation of why someone might die from being told, incorrectly by their CGM, that their blood glucose is low.
I say this as someone doesn't need to rely on a spouse but have actually received my own medical education. And I've had my own HHS patients—it's not even clear if your wife (!!) works in this area.
As the sibling commentator shares, we don't really expect these patients to show up after a day of bad data, but we also have no idea how many days of bad data occurred.
As someone that experienced DKA when I was young I'm still not sure how that happens unless there were a lot of other confounding factors. Having hypoglycemia that high for a while will make everything start smelling like varnish. Also you start physically hurting especially your kidneys which is not something you can ignore.
If there were other confounding factors then I'm wondering what their endo told them, unless this is one of those countries you could buy it without a prescription? Any endo with any training would have a fragile diabetic using more than one monitoring method and have them doing regular blood tests.
DKA is a common presenting symptom for new T1DM patients but that's definitely not the only time it occurs. And we also have HHS which can occur in T1DM and T2DM.
Thank you for offering your credentials. By nature of this being an internet, tech-focused forum there just aren't many doctors here. Without a reference to credentials, I made a (poor) assumption about your authority on the matter. I was very clear that I probably know more than the average person, but I'm certainly not an authority.
I do think my underlying point is generally, correct, though. And, implicitly supported by your retort. Low and high blood sugar are emergencies of different acuity. To be clear, by the time either of them turns into an emergency, they are both emergencies. However, the time frame for going from "my blood sugar is managed" to "I need emergency intervention" is generally different (and longer for high blood sugar emergencies).
I'll respond to the sibling poster with the same content—yes, DKA won't cause coma as quickly as insulin overdose but it can indeed come on acutely and it absolutely does kill people.
I'm a bit frustrated by the number of people on this page who are saying that high BG readings aren't an emergency; the timeline to death isn't weeks or months or 'next time I get to urgent care' but instead 'later today' or 'early tomorrow'.
DKA may be precipitated by infection (like the seasonal flu), and in that setting, worsened further by an unreliable CGM.
- https://pubmed.ncbi.nlm.nih.gov/40811481/ (pregnant women can have DKA irrespective of blood glucose readings due to changes in normal range attributable to pregnancy)
It seems like you're missing the distinction being drawn between high blood sugar (but adequate levels of insulin to prevent ketosis) and very very lowlevels of insulin. The former is bad over longer time scales; the latter can become ketosis/acidosis/an emergency quickly.
But neither that, nor is whether he should offer credentials the point. The point is you said this:
> > > Sorry to be crass, but this type of argument is exactly why non-experts shouldn't be talking about topics they aren't experts on.
I think there's a little recalibration necessary if the person you said this to turns out to be pretty well educated and capable in the subject.
> Actually a PhD is a con, not a bonus if you want normal jobs.
Depends on the market, which is true for any field. In places where there's a lot of technical work to be done, employers can hire PhD's and will do so if there's a local supply.
> Did Instagram have their LLM analyze the post and then only post generated slob when it concluded the post came from a woman? Certainly not.
I actually am sympathetic to your confusion—perhaps this is semantics, but I agree with the trivialization of the human experience assessment from the author and your post, but don't read it as an attack on women's pain as such. I think the algorithm sensed that the essay would touch people and engender a response.
--
However, I am certain that Instagram knows the author is a woman, and that the LLM they deployed can do sentiment analysis (or just call the Instagram API and ask whether the post is by a woman). So I don't think we can somehow absolve them of cultural awareness. I wonder how this sort of thing influences its output (and wish we didn't have to puzzle over such things).
> Banks [...] will face meaningful consequences for getting this wrong with any regularity
That's false, unfortunately. There's amazing levels of discretion that banks enjoy and minimal accountability to end users. The CFPB (in the USA, anyway) was a countermeasure but has been recently weakened.
That's what the OP is saying.
reply