New Systematic Review Showing General Population Prevalence of Exocrine Pancreatic Insufficiency Is Higher Than In Co-Conditions

For those unfamiliar with academic/medical journal publishing, it is slow. Very slow. I did a systematic review on EPI prevalence and submitted it to a journal on May 5, 2023. It underwent peer review and a round of revisions and was accepted on July 13, 2023. (That part is actually relatively quick.) However, it sat, and sat, and sat, and sat, and sat. I was impatient and wrote a blog post last year about the basic premise of the review, which is that despite commonly repeated statements about the prevalence of EPI being so high in co-conditions that those conditions therefore are the highest drivers of EPI… this unlikely to be true because it is mathematically improbable.

And then this paper still sat several more months until it was published online ahead of print…today! Wahoo! You can read “An Updated Review of Exocrine Pancreatic Insufficiency Prevalence finds EPI to be More Common in General Population than Rates of Co-Conditions in the Journal of Gastrointestinal and Liver Diseases ahead of print (scheduled for the March 2024 issue).

It’s open access (and I didn’t have to pay for it to be!), so click here to go read it and download your own PDF copy of the article there. (As a reminder, I also save a version of every article including those that are not open access at DIYPS.org/research, in case you’re looking for this in the future or want to read some of my other research.) If you don’t want to read the full article, here’s a summary below and key takeaways for providers and patients (aka people like me with EPI!).

I read and systematically categorized 649 articles related to exocrine pancreatic insufficiency, which is known as EPI or PEI depending on where in the world you are. EPI occurs when the pancreas no longer produces enough enzymes to successfully digest food completely; when this occurs, pancreatic enzyme replacement therapy (PERT) is needed. This means swallowing enzyme pills every time you eat or drink something with fat or protein in it.

Like many of my other EPI-related research articles, this one found that EPI is underdiagnosed; undertreated; treatment costs are high; and prevalence is widely misunderstood, possibly leading to missing screening key populations.

  • Underdiagnosis – for a clearer picture and specific disease-related example of how EPI is likely underdiagnosed in a co-condition, check out my other systematic review specifically assessing EPI in diabetes. I show in that paper how EPI is likely many times more likely than gastroparesis and celiac disease, yet it’s less likely to be screened for.
  • Undertreated – another recent systematic review that I wrote after this paper (but was published sooner) is this systematic review on PERT dosing guidelines and dosing literature, showing how the overwhelming majority of people are not prescribed enough enzymes to meet their needs. Thus, symptoms persist and the literature continues to state that symptoms can’t be managed with PERT, which is not necessarily true: it just hasn’t been studied correctly with sufficient titration protocols.
  • PERT costs are high – I highlight that although PERT costs continue to rise each year, there are studies in different co-condition populations showing PERT treatment is cost-effective and in some cases reduces the overall cost of healthcare. It’s hard to believe when we look at the individual out of pocket costs related to PERT sometimes, but the data more broadly shows that PERT treatment in many populations is cost-effective.
  • Prevalence of EPI is misunderstood. This is the bulk of the paper and goes into a lot of detail showing how the general population estimates of EPI may be as high as 11-21%. In contrast, although prevalence of EPI is much higher within co-conditions, these conditions are such a small fraction of the general population that they therefore are also likely a small fraction of the EPI population.

As I wrote in the paper:

“The overall population prevalence of cystic fibrosis, pancreatitis, cancer, and pancreatic-related surgery combined totals <0.1%, and the lower end of the estimated overall population prevalence of EPI is approximately 10%, which suggests less than 1% of the overall incidence of EPI occurs in such rare co-conditions.

We can therefore conclude that 99% of EPI occurs in those without a rare co-condition.”

I also pointed out the mismatch of research prioritization and funding to date in EPI. 56-85% of the EPI-related research is focused on those representing less than ~1% of the overall population with EPI.

So what should you take away from this research?

If you are a healthcare provider:

Make sure you are screening people who present with gastrointestinal symptoms with a fecal elastase test to check for EPI. Weight loss and malnutrition does not always occur with EPI (which is a good thing, meaning it’s caught earlier) and similarly not everyone has diarrhea as their hallmark symptoms. Messy, smelly stools are often commonly described by people with EPI, among other symptoms such as excess gas and bloating,

Remember that conditions like diabetes have a high prevalence of EPI – it’s not just chronic pancreatitis or cystic fibrosis.

If you do have a patient that you are diagnosing or have diagnosed with EPI, make sure you are aware of the current dosing guidelines (see this systematic review) and 1) prescribe a reasonable minimal starting dose; 2) tell the patient when/how they can adjust their PERT on their own and when to call back for an updated prescription as they figure out what they need, and; 3) tell them they will likely need an updated prescription and you are ready to support them when they need to do so.

If you are a person living with EPI:

Most people with EPI are not taking enough enzymes to eliminate their symptoms. Dose timing matters (take it with/throughout meals), and the quantity of PERT matters.

If you’re still having symptoms, you may still need more enzymes.

Don’t compare what you are doing to what other people are taking: it’s not a moral failing to need a different amount of enzymes (or insulin, for that matter, or any other medication) than another person! It also likely varies by what we are eating, and we all eat differently.

If you’re still experiencing symptoms, you may need to experiment with a higher dose. If you still have symptoms or have new symptoms that start after taking PERT, you may need to try a different brand of PERT. Some people do well on one but not another, and there are different kinds you can try – ask your doctor.

How to cite this systematic review:

Lewis D. An Updated Review of Exocrine Pancreatic Insufficiency Prevalence finds EPI to be More Common in General Population than Rates of Co-Conditions. Journal of Gastrointestinal and Liver Diseases. 2024. DOI: 10.15403/jgld-5005

For other posts related to EPI, see DIYPS.org/EPI for more of my personal experiences with EPI and other plain-language research summaries.

For other research articles, see DIYPS.org/research

A systematic review shows EPI prevalence is more common in the general population than in co-conditions

Meet me in the gray area: beyond prevention, before progression

Two things can simultaneously be true:

  • Doctors may wish they had more opportunities to help patients prevent having worse/later stage outcomes of a disease.
  • Doctors may struggle when a patient seeks health care at an early stage, asking for strategies and intervention support against developing worse/later stage outcomes of a disease.

The struggle may be for a few reasons. There’s often a lack of systemic infrastructure to support patients who show up earlier rather than later in a disease progression, especially when the frequency/timeline of care is much quicker than the system is currently resourced for. There’s often a lack of research for these earlier stages and what effective strategies are for preventing progression and treating earlier stage outcomes.

When a clinician struggles with this, it’s not a moral failing of the clinician if they don’t feel equipped to tackle those challenges. However, I do wish clinicians would more often clearly communicate to patients about these struggles. The patient might have a choice: do they pursue another clinician who might have different resources (including time/energy) or expertise in navigating the unknown? Or do they work with the existing clinician to navigate the murky waters together, figuring it out as they go? But patients only have a choice if they realize it themselves and are equipped to pursue alternative paths – or are told that this is a fork in the path.

The challenge is this is a gray area for all of us – patients and clinicians alike. But the reality is, the gray area (for a patient) betwixt and between prevention and progression is our life. The black and white that may emerge after the gray space can be as significant, literally, as life and death. We as patients are highly motivated to navigate the gray area and reduce suffering and possibly try different or new strategies that have shown early promise (although maybe haven’t yet been tested to RCT or the ideal standard, or in the specific disease or stage of the disease in question). We as patients may not have time to wait for the evidence to evolve further.

Clinicians may be aware of the gray space that the patient has landed in. The reality that many clinicians may not know or forget – or have slipped out of their mind – is that the gray space is even more daunting to face alone. If the instinct is to simply shoot down every patient idea with “that’s not approved for use in this disease” without forthrightly contextualizing against a recognition “there’s nothing tested or proven for this part/stage of the disease”, it can begin to put cracks in a relationship. What clinicians might not realize is that a patient may not have time to be in the gray space with a clinician who simply says no to trying anything, because no one has ever studied it before and when little study is being done at all about the gray area the patient is within. Or maybe clinicians do realize it, and sometimes rely on the power of the broken systemic infrastructure that keeps a patient from finding a clinician who does feel equipped to walk through the gray area with them.

What I wish is for clinicians to be equipped to identify this situation, standing on the edge of the gray area with a patient. And to say up front, then and there, if they don’t feel comfortable pursuing off-label strategies when there are zero documented on-label strategies beyond waiting for the worse outcomes to progress. I don’t like that (because why wait for permanent damage to do something, when permanent damage is not inevitable if action is taken sooner), but I very much highly respect and appreciate a clinician who is forthright and willing to say they don’t have time/energy/feel equipped to do so.

Why? Because if I’m already in the gray space, past prevention and before serious progression, it gives me a better opportunity to find someone else who can partner there. It might take a try or two, but it keeps me from wasting time and energy and trying to invest in developing a relationship with a clinician who has already decided they can’t help me until I cross over into black and white worse outcomes.

When we talk about prevention, it’s often about preventing a disease. In the world I live in, and the body I live in – now inhibited by five autoimmune diseases, I don’t have a choice about disease prevention for the most part. My body is clearly equipped with a superstar hyperactive immune system. While I’ve seen some research working on addressing autoimmune stuff, it’s likely decades away from any cure of any one condition that I have (let alone all of them) or fixing the hyperactivity of my immune system and preventing additional autoimmune diseases. Sure, I can work to prevent other diseases that aren’t autoimmune (exercising, staying in as best health overall that I can, etc.), but my focus right now is keeping each of my five autoimmune conditions from being bigger headaches than they already are.

(As a side note, I recently read this paper looking at rates of autoimmune conditions after T1D, based on a registry analysis in Sweden of people with T1D. It’s interesting that the risk of “one more” condition following T1D is 17%, two more is essentially the square of that, etc. etc. all the way down…so the risk is typically about 17% and it’s not additive; having two does not mean you’re more likely to get three, it means you have about the same 17% chance of something else. That’s a useful mental model to me, understanding that I got unlucky 4 more times…and that combination of luck is rare among people with T1D. They went all the way to the category of “three or more” autoimmune conditions after T1D, calculating that 0.3% of people with T1D have 3 or more autoimmune conditions after T1D. They stopped there, but you can extrapolate by multiplying by 17% again and estimate it’s 0.08% for four or more…which is where I’m at. This shows me that I’m not alone in dealing with so many things, but it puts me at about 1 in 1,250 of people with T1D or around one in a million – heh – in the general population if you extrapolate based on global population estimates and assume similar rates/risks of autoimmune conditions in the general public.)

Four of the five are easy enough (although, the fourth took about a year and a half to get to ‘easy enough’, overlapping with the third taking two to three years). The fifth, though, is the gray area that I currently inhabit. Possibly because I am in tune with my body because of the experience with these other autoimmune conditions, I have been presenting to the healthcare system to address this fifth autoimmune condition earlier than most people. Like many autoimmune conditions, it takes years to decades for some people to get diagnosed. Many are diagnosed after systemic manifestations have fully kicked in, e.g. these later stage worse outcomes I referred to above. I’m in a gray area, at the edge of seeing systemic activity, and able to identify it as a red flag, but before – I hope – permanent irreversible damage has been done. The question remains, however, for me to figure out how to navigate this gray area and with which clinicians, in order to achieve care that will possibly prevent or delay or reduce the severity of the outcomes that I will end up with.

I speak from personal experience with this gray area. It’s not fun to navigate, even if you do have a really great clinician partner. But it’s infinitely more challenging to stand there in the gray, unsure of the ability or willingness of a clinician to partner with you.

Meet me in the gray: beyond prevention, before progression - a blog written by Dana M. Lewis on DIYPS.org

A Slackbot for using Slack to access and use a chat-based LLM in public

I’ve been thinking a lot about how to help my family, friends, and colleagues use LLMs to power their work. (As I’ve written about here, and more recently here with lots of tips on prompting and effectively using LLMs for different kinds of projects). 

Scott has been on the same page, especially thinking about how to help colleagues use LLMs effectively, but taking a slightly different approach: he built a Slackbot (a bot for Slack) which uses GPT-3.5 and GPT-4 to answer questions. This uses the API of GPT but presents it to the user in Slack instead of having to use ChatGPT as the chat interface. So, it’s a LLM chatbot, different than ChatGPT (because it’s a different chat interface), but uses the same AI (GPT-3.5 and GPT-4 from OpenAI). You could implement the same idea (a chat-based bot in Slack) using different AIs/LLMs, of course.

Using a slack-based bot for an LLM achieves a couple of things:

  1. More people can try GPT-4 and compare it to GPT-3.5 to get a taste for prompting and responses, without having to pay $20/month for a ChatGPT Pro account to get access to GPT-4.
  2. If you spend a lot of time in Slack for work, you don’t have to switch windows to access GPT.
  3. If your employer doesn’t want you to use the ChatGPT consumer product for work due to security concerns, but is more comfortable with OpenAI’s confidentiality guarantees for their API, a Slack bot interface provides a more secure alternative.
  4. You can see “in public” how other people in your Slack workspace are using it, and learn from their prompts and interactions new tricks and ideas (in addition to reading my long post here with lots of tips and suggestions).
  5. You can privately (in DM by yourself) talk to the bot and ask it your “dumb” questions (which aren’t dumb), and you can reason through things at your own speed or learn how to do things that you haven’t done before, and do so in private just like if you had your own ChatGPT account. It doesn’t burn social capital or take other people’s time, which you can save for more nuanced questions.

Scott has implemented it for work, but also came up with another fun use for it: we created a family-focused Slack channel for kids in our lives (we have ten (!) nieces and nephews – you can see how I used GPT to help with special custom books for some of them recently) so their parents and they can access GPT in a safe environment, too. ChatGPT (and OpenAI’s GPT API) have some reasonable safeguards in it already to protect kids, but more usefully we want to be able to provide custom instructions to keep it always at a kid-focused level. Plus this way we can share the experience with them, too.

I asked the bot to summarize itself for a lay audience not familiar with the project, and this was the output:

### Summary of the SlackAskBot

The SlackAskBot is a smart assistant designed to operate within Slack, a popular communication platform used by teams for messaging and collaboration. Imagine having a helpful robot in your group chats or direct messages that can understand your questions and provide informative responses. That’s what the SlackAskBot does. It’s like adding a knowledgeable team member to your Slack workspace who is always ready to assist.

#### How It Works:

  1. **Integration with Slack:**

– The bot is integrated into Slack, meaning it can read messages in channels it’s added to or when directly messaged. It’s like inviting a friend into your group chat who can listen and respond to conversations.

  1. **Understanding Messages:**

– When you type a message that includes the bot (either by mentioning it with an @ symbol in a channel or by sending it a direct message), the bot pays attention. It’s designed to understand that you’re talking to it and that you’re expecting some form of response.

  1. **Processing Your Requests:**

– Once the bot receives a message, it doesn’t just look at the latest message you’ve sent. It considers the context by looking at the conversation history. This way, it can provide responses that make sense within the ongoing discussion. It’s akin to a human joining a conversation, where understanding the previous discussion points is crucial for making relevant comments.

  1. **Generating Responses:**

– The bot uses a powerful language model (think of it as a very advanced AI that understands and generates human-like text) to come up with responses to your messages. It’s as if the bot thinks about what you’ve asked and then crafts a reply that aims to be helpful and informative.

  1. **Interacting Back:**

– After thinking through your message and generating a response, the bot then sends this response back into the Slack channel or direct message. You’ll see its reply just like you would from any other team member, providing the information or assistance you requested.

  1. **Special Features:**

– The bot is designed with specific settings for different channels or direct messages. This means it can tailor its responses based on where it’s talking. For example, it might respond differently in a casual chat compared to a more formal project discussion channel.

  1. **Respecting Privacy and Permissions:**

– The bot is programmed to respect Slack’s rules and the privacy of your conversations. It only listens and responds to messages where it’s explicitly mentioned or directly messaged, ensuring that it doesn’t intrude on private discussions.

#### In Summary:

The SlackAskBot acts as a virtual assistant within your Slack workspace, ready to provide information and answers to your questions. It’s designed to understand the context of conversations, generate helpful responses, and interact with users in a way that enhances team communication and productivity. Whether you’re asking for quick facts, seeking advice on a project, or just interacting for fun, the SlackAskBot is there to make your Slack experience more informative and engaging.


The SlackAskBot is open source – you can check out the code and instructions for how to implement it in your own Slack environment in the repository here.

We are using Slack as a chat interface for LLMs like GPT, making the user experience similar to ChatGPT

Effective Pair Programming and Coding and Prompt Engineering and Writing with LLMs like ChatGPT and other AI tools

I’ve been puzzled when I see people online say that LLM’s “don’t write good code”. In my experience, they do. But given that most of these LLMs are used in chatbot mode – meaning you chat and give it instructions to generate the code – that might be where the disconnect lies. To get good code, you need effective prompting and to do so, you need clear thinking and ideas on what you are trying to achieve and how.

My recipe and understanding is:

Clear thinking + clear communication of ideas/request = effective prompting => effective code and other outputs

It also involves understanding what these systems can and can’t do. For example, as I’ve written about before, they can’t “know” things (although they can increasingly look things up) and they can’t do “mental” math. But, they can generally repeat patterns of words to help you see what is known about a topic and they can write code that you can execute (or it can execute, depending on settings) to solve a math problem.

What the system does well is help code small chunks, walk you through processes to link these sections of code up, and help you implement them (if you ask for it). The smaller the task (ask), the more effective it is. Or also – the easier it is for you to see when it completes the task and when it hasn’t been able to finish due to limitations like response length limits, information falling out of the context window (what it knows that you’ve told it); unclear prompting; and/or because you’re asking it to do things for which it doesn’t have expertise. Some of the last part – lack of expertise – can be improved with specific prompting techniques –  and that’s also true for right-sizing the task it’s focusing on.

Right-size the task by giving a clear ask

If I were to ask an LLM to write me code for an iOS app to do XYZ, it could write me some code, but it certainly wouldn’t (at this point in history, written in February 2024), write all code and give me a downloadable file that includes it all and the ability to simply run it. What it can do is start writing chunks and snippets of code for bits and pieces of files that I can take and place and build upon.

How do I know this? Because I made that mistake when trying to build my first iOS apps in April and May 2023 (last year). It can’t do that (and still can’t today; I repeated the experiment). I had zero ideas how to build an iOS app; I had a sense that it involved XCode and pushing to the Apple iOS App Store, and that I needed “Swift” as the programming language. Luckily, though, I had a much stronger sense of how I wanted to structure the app user experience and what the app needed to do.

I followed the following steps:

  1. First, I initiated chat as a complete novice app builder. I told it I was new to building iOS apps and wanted to use XCode. I had XCode downloaded, but that was it. I told it to give me step by step instructions for opening XCode and setting up a project. Success! That was effective.
  2. I opened a different chat window after that, to start a new chat. I told it that it was an expert in iOS programming using Swift and XCode. Then I described the app that I wanted to build, said where I was in the process (e.g. had opened and started a project in XCode but had no code yet), and asked it for code to put on the home screen so I could build and open the app and it would have content on the home screen. Success!
  3. From there, I was able to stay in the same chat window and ask it for pieces at a time. I wanted to have a new user complete an onboarding flow the very first time they opened the app. I explained the number of screens and content I wanted on those screens; the chat was able to generate code, tell me how to create that in a file, and how to write code that would trigger this only for new users. Success!
  4. I was able to then add buttons to the home screen; have those buttons open new screens of the app; add navigation back to the home; etc. Success!
  5. (Rinse and repeat, continuing until all of the functionality was built out a step at a time).

To someone with familiarity building and programming things, this probably follows a logical process of how you might build apps. If you’ve built iOS apps before and are an expert in Swift programming, you’re either not reading this blog post or are thinking I (the human) am dumb and inexperienced.

Inexperienced, yes, I was (in April 2023). But what I am trying to show here is for someone new to a process and language, this is how we need to break down steps and work with LLMs to give it small tasks to help us understand and implement the code it produces before moving forward with a new task (ask). It takes these small building block tasks in order to build up to a complete app with all the functionality that we want. Nowadays, even though I can now whip up a prototype project and iOS app and deploy it to my phone within an hour (by working with an LLM as described above, but skipping some of the introductory set-up steps now that I have experience in those), I still follow the same general process to give the LLM the big picture and efficiently ask it to code pieces of the puzzle I want to create.

As the human, you need to be able to keep the big picture – full app purpose and functionality – in mind while subcontracting with the LLM to generate code for specific chunks of code to help achieve new functionality in our project.

In my experience, this is very much like pair programming with a human. In fact, this is exactly what we did when we built DIYPS over ten years ago (wow) and then OpenAPS within the following year. I’ve talked endlessly about how Scott and I would discuss an idea and agree on the big picture task; then I would direct sub-tasks and asks that he, then also Ben and others would be coding on (at first, because I didn’t have as much experience coding and this was 10 years ago without LLMs; I gradually took on more of those coding steps and roles as well). I was in charge of the big picture project and process and end goal; it didn’t matter who wrote which code or how; we worked together to achieve the intended end result. (And it worked amazingly well; here I am 10 years later still using DIYPS and OpenAPS; and tens of thousands of people globally are all using open source AID systems spun off of the algorithm we built through this process!)

Two purple boxes. The one on the left says "big picture project idea" and has a bunch of smaller size boxes within labeled LLM, attempting to show how an LLM can do small-size tasks within the scope of a bigger project that you direct it to do. On the right, the box simply says "finished project". Today, I would say the same is true. It doesn’t matter – for my types of projects – if a human or an LLM “wrote” the code. What matters is: does it work as intended? Does it achieve the goal? Does it contribute to the goal of the project?

Coding can be done – often by anyone (human with relevant coding expertise) or anything (LLM with effective prompting) – for any purpose. The critical key is knowing what the purpose is of the project and keeping the coding heading in the direction of serving that purpose.

Tips for right-sizing the ask

  1. Consider using different chat windows for different purposes, rather than trying to do it all in one. Yes, context windows are getting bigger, but you’ll still likely benefit from giving different prompts in different windows (more on effective prompting below).Start with one window for getting started with setting up a project (e.g. how to get XCode on a Mac and start a project; what file structure to use for an app/project that will do XYZ; how to start a Jupyter notebook for doing data science with python; etc); brainstorming ideas to scope your project; then separately for starting a series of coding sub-tasks (e.g. write code for the home page screen for your app; add a button that allows voice entry functionality; add in HealthKit permission functionality; etc.) that serves the big picture goal.
  2. Make a list for yourself of the steps needed to build a new piece of functionality for your project. If you know what the steps are, you can specifically ask the LLM for that.Again, use a separate window if you need to. For example, if you want to add in the ability to save data to HealthKit from your app, you may start a new chat window that asks the LLM generally how does one add HealthKit functionality for an app? It’ll describe the process of certain settings that need to be done in XCode for the project; adding code that prompts the user with correct permissions; and then code that actually does the saving/revising to HealthKit.

    Make your list (by yourself or with help), then you can go ask the LLM to do those things in your coding/task window for your specific project. You can go set the settings in XCode yourself, and skip to asking it for the task you need it to do, e.g. “write code to prompt the user with HealthKit permissions when button X is clicked”.

    (Sure, you can do the ask for help in outlining steps in the same window that you’ve been prompting for coding sub-tasks, just be aware that the more you do this, the more quickly you’ll burn through your context window. Sometimes that’s ok, and you’ll get a feel for when to do a separate window with the more experience you get.)

  • Pay attention as you go and see how much code it can generate and when it falls short of an ask. This will help you improve the rate at which you successfully ask and it fully completes a task for future asks. I observe that when I don’t know – due to my lack of expertise – the right size of a task, it’s more prone to give me ½-⅔ of the code and solution but need additional prompting after that. Sometimes I ask it to continue where it cut off; other times I start implementing/working with the bits of code (the first ⅔) it gave me, and have a mental or written note that this did not completely generate all steps/code for the functionality and to come back.Part of why sometimes it is effective to get started with ⅔ of the code is because you’ll likely need to debug/test the first bit of code, anyway. Sometimes when you paste in code it’s using methods that don’t match the version you’re targeting (e.g. functionality that is outdated as of iOS 15, for example, when you’re targeting iOS 17 and newer) and it’ll flag a warning or block it from working until you fix it.

    Once you’ve debugged/tested as much as you can of the original ⅔ of code it gave you, you can prompt it to say “Ok, I’ve done X and Y. We were trying to (repeat initial instructions/prompt) – what are the remaining next steps? Please code that.” to go back and finish the remaining pieces of that functionality.

    (Note that saying “please code that” isn’t necessarily good prompt technique, see below).

    Again, much of this is paying attention to how the sub-task is getting done in service of the overall big picture goal of your project; or the chunk that you’ve been working on if you’re building new functionality. Keeping track with whatever method you prefer – in your head, a physical written list, a checklist digitally, or notes showing what you’ve done/not done – is helpful.

Most of the above I used for coding examples, but I follow the same general process when writing research papers, blog posts, research protocols, etc. My point is that this works for all types of projects that you’d work on with an LLM, whether the output generation intended is code or human-focused language that you’d write or speak.

But, coding or writing language, the other thing that makes a difference in addition to right-sizing the task is effective prompting. I’ve intuitively noticed that has made the biggest difference in my projects for getting the output matching my expertise. Conversely, I have actually peer reviewed papers for medical journals that do a horrifying job with prompting. You’ll hear people talk about “prompt engineering” and this is what it is referring to: how do you engineer (write) a prompt to get the ideal response from the LLM?

Tips for effective prompting with an LLM

    1. Personas and roles can make a difference, both for you and for the LLM. What do I mean by this? Start your prompt by telling the LLM what perspective you want it to take. Without it, you’re going to make it guess what information and style of response you’re looking for. Here’s an example: if you asked it what caused cancer, it’s going to default to safety and give you a general public answer about causes of cancer in very plain, lay language. Which may be fine. But if you’re looking to generate a better understanding of the causal mechanism of cancer; what is known; and what is not known, you will get better results if you prompt it with “You are an experienced medical oncologist” so it speaks from the generated perspective of that role. Similarly, you can tell it your role. Follow it with “Please describe the causal mechanisms of cancer and what is known and not known” and/or “I am also an experienced medical researcher, although not an oncologist” to help contextualize that you want a deeper, technical approach to the answer and not high level plain language in the response.

      Compare and contrast when you prompt the following:

      A. “What causes cancer?”

      B. “You are an experienced medical oncologist. What causes cancer? How would you explain this differently in lay language to a patient, and how would you explain this to another doctor who is not an oncologist?”

      C. “You are an experienced medical oncologist. Please describe the causal mechanisms of cancer and what is known and not known. I am also an experienced medical researcher, although not an oncologist.”

      You’ll likely get different types of answers, with some overlap between A and the first part of answer B. Ditto for a tiny bit of overlap between the latter half of answer B and for C.

      I do the same kind of prompting with technical projects where I want code. Often, I will say “You are an expert data scientist with experience writing code in Python for a Jupyter Notebook” or “You are an AI programming assistant with expertise in building iOS apps using XCode and SwiftUI”. Those will then be followed with a brief description of my project (more on why this is brief below) and the first task I’m giving it.

      The same also goes for writing-related tasks; the persona I give it and/or the role I reference for myself makes a sizable difference in getting the quality of the output to match the style and quality I was seeking in a response.

  • Be specific. Saying “please code that” or “please write that” might work, sometimes, but more often or not will get a less effective output than if you provide a more specific prompt.I am a literal person, so this is something I think about a lot because I’m always parsing and mentally reviewing what people say to me because my instinct is to take their words literally and I have to think through the likelihood that those words were intended literally or if there is context that should be used to filter those words to be less literal. Sometimes, you’ll be thinking about something and start talking to someone about something, and they have no idea what on earth you’re talking about because the last part of your out-loud conversation with them was about a completely different topic!

    LLMs are the same as the confused conversational partner who doesn’t know what you’re thinking about. LLMs only know what you’ve last/recently told it (and more quickly than humans will ‘forget’ what you told it about a project). Remember the above tips about brainstorming and making a list of tasks for a project? Providing a description of the task along with the ask (e.g. we are doing X related to the purpose of achieving Y, please code X) will get you better output more closely matching what you wanted than saying “please code that” where the LLM might code something else to achieve Y if you didn’t tell it you wanted to focus on X.

    I find this even more necessary with writing related projects. I often find I need to give it the persona “You are an expert medical researcher”, the project “we are writing a research paper for a medical journal”, the task “we need to write the methods section of the paper”, and a clear ask “please review the code and analyses and make an outline of the steps that we have completed in this process, with sufficient detail that we could later write a methods section of a research paper”. A follow up ask is then “please take this list and draft it into the methods section”. That process with all of that specific context gives better results than “write a methods section” or “write the methods” etc.

  • Be willing to start over with a new window/chat. Sometimes the LLM can get itself lost in solving a sub-task and lose sight (via lost context window) of the big picture of a project, and you’ll find yourself having to repeat over and over again what you’re asking it to do. Don’t be afraid to cut your losses and start a new chat for a sub-task that you’ve been stuck on. You may be able to eventually come back to the same window as before, or the new window might become your new ‘home’ for the project…or sometimes a third, fourth, or fifth window will.
  • Try, try again.
    I may hold the record for the longest running bug that I (and the LLM) could. Not. solve. This was so, so annoying. No users apparently noticed it but I knew about it and it bugged me for months and months. Every few weeks I would go to an old window and also start a new window, describe the problem, paste the code in, and ask for help to solve it. I asked it to identify problems with the code; I asked it to explain the code and unexpected/unintended functionality from it; I asked it what types of general things would be likely to cause that type of bug. It couldn’t find the problem. I couldn’t find the problem. Finally, one day, I did all of the above, but then also started pasting every single file from my project and asking if it was likely to include code that could be related to the problem. By forcing myself to review all my code files with this problem in mind, even though the files weren’t related at all to the file/bug….I finally spotted the problem myself. I pasted the code in, asked if it was a possibility that it was related to the problem, the LLM said yes, I tried a change and…voila! Bug solved on January 16 after plaguing me since November 8. (And probably existed before then but I didn’t have functionality built until November 8 where I realized it was a problem). I was beating myself up about it and posted to Twitter about finally solving the bug (but very much with the mindset of feeling very stupid about it). Someone replied and said “congrats! sounds like it was a tough one!”. Which I realized was a very kind framing and one that I liked, because it was a tough one; and also I am doing a tough thing that no one else is doing and I would not have been willing to try to do without an LLM to support.

    Similarly, just this last week on Tuesday I spent about 3 hours working on a sub-task for a new project. It took 3 hours to do something that on a previous project took me about 40 minutes, so I was hyper aware of the time mismatch and perceiving that 3 hours was a long time to spend on the task. I vented to Scott quite a bit on Tuesday night, and he reminded me that sure it took “3 hours” but I did something in 3 hours that would take 3 years otherwise because no one else would do (or is doing) the project that I’m working on. Then on Wednesday, I spent an hour doing another part of the project and Thursday whipped through another hour and a half of doing huge chunks of work that ended up being highly efficient and much faster than they would have been, in part because the “three hours” it took on Tuesday wasn’t just about the code but about organizing my thinking, scoping the project and research protocol, etc. and doing a huge portion of other work to organize my thinking to be able to effectively prompt the LLM to do the sub-task (that probably did actually take closer to the ~40 minutes, similar to the prior project).

    All this to say: LLMs have become pair programmers and collaborators and writers that are helping me achieve tasks and projects that no one else in the world is working on yet. (It reminds me very much of my early work with DIYPS and OpenAPS where we did the work, quietly, and people eventually took notice and paid attention, albeit slower than we wished but years faster than had we not done that work. I’m doing the same thing in a new field/project space now.) Sometimes, the first attempt to delegate a sub-task doesn’t work. It may be because I haven’t organized my thinking enough, and the lack of ideal output shows that I have not prompted effectively yet. Sometimes I can quickly fix the prompt to be effective; but sometimes it highlights that my thinking is not yet clear; my ability to communicate the project/task/big picture is not yet sufficient; and the process of achieving the clarity of thinking and translating to the LLM takes time (e.g. “that took 3 hours when it should have taken 40 minutes”) but ultimately still moves me forward to solving the problem or achieving the tasks and sub-tasks that I wanted to do. Remember what I said at the beginning:

    Clear thinking + clear communication of ideas/request = effective prompting => effective code and other outputs

 

  • Try it anyway.
    I am trying to get out of the habit of saying “I can’t do X”, like “I can’t code/program an iOS app”…because now I can. I’ve in fact built and shipped/launched/made available multiple iOS apps (check out Carb Pilot if you’re interested in macronutrient estimates for any reason; you can customize so you only see the one(s) you care about; or if you have EPI, check out PERT Pilot, which is the world’s first and only app for tracking pancreatic enzyme replacement therapy and has the same AI feature for generating macronutrient estimates to aid in adjusting enzyme dosing for EPI.) I’ve also made really cool, 100% custom-to-me niche apps to serve a personal purpose that save me tons of time and energy. I can do those things, because I tried. I flopped a bunch along the way – it took me several hours to solve a simple iOS programming error related to home screen navigation in my first few apps – but in the process I learned how to do those things and now I can build apps. I’ve coded and developed for OpenAPS and other open source projects, including a tool for data conversion that no one else in the world had built. Yet, my brain still tries to tell me I can’t code/program/etc (and to be fair, humans try to tell me that sometimes, too).

    I bring that up to contextualize that I’m working on – and I wish others would work on to – trying to address the reflexive thoughts of what we can and can’t do, based on prior knowledge. The world is different now and tools like LLMs make it possible to learn new things and build new projects that maybe we didn’t have time/energy to do before (not that we couldn’t). The bar to entry and the bar to starting and trying is so much lower than it was even a year ago. It really comes down to willingness to try and see, which I recognize is hard: I have those thought patterns too of “I can’t do X”, but I’m trying to notice when I have those patterns; shift my thinking to “I used to not be able to do X; I wonder if it is possible to work with an LLM to do part of X or learn how to do Y so that I could try to do X”.

    A recent real example for me is power calculations and sample size estimates for future clinical trials. That’s something I can’t do; it requires a statistician and specialized software and expertise.

    Or…does it?

    I asked my LLM how power calculations are done. It explained. I asked if it was possible to do it using Python code in a Jupyter notebook. I asked what information would be needed to do so. It walked me through the decisions I needed to make about power and significance, and highlighted variables I needed to define/collect to put into the calculation. I had generated the data from a previous study so I had all the pieces (variables) I needed. I asked it to write code for me to run in a Jupyter notebook, and it did. I tweaked the code, input my variables, ran it..and got the result. I had run a power calculation! (Shocked face here). But then I got imposter syndrome again, reached out to a statistician who I had previously worked with on a research project. I shared my code and asked if that was the correct or an acceptable approach and if I was interpreting it correctly. His response? It was correct, and “I couldn’t have done it better myself”.

    (I’m still shocked about this).

    He also kindly took my variables and put it in the specialized software he uses and confirmed that the results output matched what my code did, then pointed out something that taught me something for future projects that might be different (where the data is/isn’t normally distributed) although it didn’t influence the output of my calculation for this project.

    What I learned from this was a) this statistician is amazing (which I already knew from working with him in the past) and kind to support my learning like this; b) I can do pieces of projects that I previously thought were far beyond my expertise; c) the blocker is truly in my head, and the more we break out of or identify the patterns stopping us from trying, the farther we will get.

    “Try it anyway” also refers to trying things over time. The LLMs are improving every few months and often have new capabilities that didn’t before. Much of my work is done with GPT-4 and the more nuanced, advanced technical tasks are way more efficient than when using GPT-3.5. That being said, some tasks can absolutely be done with GPT-3.5-level AI. Doing something now and not quite figuring it out could be something that you sort out in a few weeks/months (see above about my 3 month bug); it could be something that is easier to do once you advance your thinking ; or it could be more efficiently done with the next model of the LLM you’re working with.

  • Test whether custom instructions help. Be aware though that sometimes too many instructions can conflict and also take up some of your context window. Plus if you forget what instructions you gave it, you might get seemingly unexpected responses in future chats. (You can always change the custom instructions and/or turn it on and off.)

I’m hoping this helps give people confidence or context to try things with LLMs that they were not willing to try before; or to help get in the habit of remembering to try things with LLMs; and to get the best possible output for the project that they’re working on.

Remember:

  • Right-size the task by making a clear ask.
  • You can use different chat windows for different levels of the same project.
  • Use a list to help you, the human, keep track of all the pieces that contribute to the bigger picture of the project.
  • Try giving the LLM a persona for an ask; and test whether you also need to assign yourself a persona or not for a particular type of request.
  • Be specific, think of the LLM as a conversational partner that can’t read your mind.
  • Don’t be afraid to start over with a new context window/chat.
  • Things that were hard a year ago might be easier with an LLM; you should try again.
  • You can do more, partnering with an LLM, than you can on your own, and likely can do things you didn’t realize were possible for you to do!

Clear thinking + clear communication of ideas/request = effective prompting => effective code and other outputs

Have any tips to help others get more effective output from LLMs? I’d love to hear them, please comment below and share your tips as well!

Tips for prompting LLMs like ChatGPT, written by Dana M. Lewis and available from DIYPS.org