The theme of the month is SYSTEMS - refining the systems I have to ensure clarity and maximising the time and resources I mindfully spent. This means putting many limits on what I used to do e.g. having only one social engagement per day, putting limits to my spending.
This also means having a deep look at my systems to make sure they are running as smoothly as they can. When the chaos starts to pick up, we won’t have the presence to look at our own machine and check that it is performing as well as possible. This naturally primes the reading towards the building and streamlining of systems.
1 | Tim Ferriss Show #694: Sam Corcos
As the CEO of Levels Health. Sam Corcos has been extremely vocal on his insights on effective delegation and knowledge management.When creating a new component in a system, there will be a need to maintain it to continue its use in the system. This adds work continuously for every new process or component.
Every new surface that you add is an obligation to maintain — maybe forever.
Lesson: Make sure the benefit continues to outweigh the cost, and keep that cost in mind.
2 | ChatGPT as muse, not oracle
I first heard Geoffrey Litt in the podcast he did with Dan Shipper, and since then started devouring his writing.
On the tactical aspect: we can use LLMs to create alternative flows to conversations, instead of the linear format we are used to. We take advantage of the speed to generate many possible ways to steer the interaction, and not having to rely on the LLM’s judgement, nor verbose prompting.
One strategy I like here is to ask a model to generate many possible future paths for the conversation, and let me choose which path to follow next. Often there are many mediocre paths and one or two interesting ones. This would be really bizarre to do in a live human conversation, but plays to the strengths of models: running fast and generating lots of options.
Lesson: when prompting, create a template for a few different options. Here’s one that I use (and adapted from Geoffrey Litt’s approach:
Have a dialogue with me about an idea that I have. Each time I respond, I’d like you to respond with multiple numbered options for continuing the dialogue, following the templates below. Then I will pick a number and continue the conversation from there.
1: Reference: mention an idea from past work and academic literature in one of your areas of expertise, which you’re reminded of by my point. The readings should be from uncommon sources, which are rich in insights.
2: Push back: express skepticism about part of my idea (via assumptions made, or unclear logic), and explain why
3: Riff: Suggest a new, specific, and interesting idea based on my idea. The new idea should be in a different context, and be able to generate fun and excitement.
4: Change the topic: Ask me a question about another topic that’s relevant to our discussion
5: Ask to elaborate: Ask me to give more detail or clarify part of my point, which is unclear to someone who is well versed in first principles thinking.
3 | The Hidden Value of Deep Technical Knowledge
Written by Andrew Ng, this reminds me to not blindly use the shiny new thing, and to continue developing my own insight. That allows me to use the shiny new thing even better.
Technical depth also helps you to decide when you can’t tell what’s likely to work in advance, and when the best approach is to try a handful of promising prompts, get a result, and keep iterating.
4 | How to use ChatGPT for Psychological Growth
Dr Gena Gorlin is a Clinical Associate Professor in the Department of Psychology at the University of Texas at Austin. I chanced upon an article written by her while inhaling the Every newsletter.
This writing describes an experiment with ChatGPT discussing feelings, thoughts, and decisions.
…there’s a subtle further task I often perform as a coach or therapist when helping clients clarify their values: I listen for implicit, possibly unchecked assumptions about themselves or the world that may be coloring the values they articulateThere is a short way to doing things, and there is a roundabout way that doesn’t achieve anything.
Lesson: LLMs may not do all the work for you, but look out for the small things that you hate or find difficult. That is where the potential is in unblocking what we do best.
5 | Why Has Nobody Told Me This Before
Stepping away from LLMs here. While I have a lot of excitement in these, I admit a serious approach would need keeping myself in the game mentally. For that, I studied Dr Julie Smith.
Dr Julie Smith is known for her engaging approach to mental health education, particularly through her social media presence. She has successfully leveraged social media platforms to break down complex psychological concepts into accessible, relatable content.
Her book teaches accessible tools we can use in caring for our own mental health. The most important thing is that we must remember to use them, and be fluent in those tools.
Tools might look great in the box. But they only help when you get them out and start practising how to use them. Each tool takes regular practice. If you miss the nail with the hammer this time, come back later and try again.