I’m finishing up my read through of “The Art & Business Of Ghostwriting” by Nicolas Cole. The best chapter is Chapter. 16: Crafting Your Irresistible Ghostwriting Offer(3 Key Components). It’s a great book. I don’t want to ghostwrite, but there’s really good advice in there and it’s well written. Anyway, Chapter 16 has a framework for crafting an offer. Not new, much like the material from Russell Brunson and Alex Hormozi, but it’s well presented. ...
I’ve read a ton of books on health, nutrition, and specifically “low carb” over the years. The one’s I’ve re-read the most are by Fung/Taubes/etc., for example: The Obesity Code (Fung) Why We Get Fat (Taubes) The Case for Keto (Taubes) Good Calories, Bad Calories (Taubes) And on… I don’t spam friends/family about eating low carb (my wife is already on-board), but I am asked why I re-read books on the topic so often, especially since I’m not involved in health/nutrition in any way. ...
We all should be making our custom readers. I tripped over another banger tweet by Andrej Karpathy: Last ~hour I built a custom LLM reader app so while I read Wealth of Nations I can ask questions about any paragraph. When you click a paragraph and “Ask” it calls an LLM, builds context window of what this is, copy pastes the full chapter, the paragraph, and the question. Works great. Here’s the tweet: ...
Consider receiving an an occasional nudge. We might get these sporadically and indirectly in a work environment. You’re “thinking” or browsing the web, a college wonders over, you talk, it shake you lose and you get back to work. So, we can bot-ify this, but better? Drop in the daily TODO’s into doc, have an LLM check the doc and monitor your screen or project directory. They can then decide how and when to give you a little nudge to “get back to it” or “push beyond”. ...
I love the movie Gattaca. I’ve probably watched it a dozen times since I first saw it in the late 1990s. Especially when dvd’s were a thing. These days, it’s very hard to find if and where an old classic is available. Anyway, here’s a synopsis of the movie via our friend gpt4o: Gattaca (1997) is a sci-fi thriller set in a dystopian future where genetic engineering determines a person’s social status and opportunities. The story follows Vincent Freeman, a naturally conceived “in-valid” with genetic imperfections that limit his aspirations. He dreams of traveling to space but is denied entry into the prestigious Gattaca Aerospace Corporation due to his inferior genetics. ...
Like most programmers, I’ve been thinking a lot about the future of programming. There’s a lot of chatter on the wild web that given LLMs can generate snippets, functions and even whole scripts based on prompts, and they’re often very good, that we’re headed to a world where human-written code may be less and less likely. We’re collaborating on code for now, but that won’t last. We will first alpha-go and then stockfish professional programmers out of existence. ...
It seems that longevity and extending healthspan are hot topics again. Sure. Who doesn’t want a long healthy life? My thinking is to stick to the basics and do them well. Stick to the stuff that does not change and probably will not change, regardless of new fads, fashions and “scientific discoveries”. Stuff like: Clean eating Eat whole foods Eat protein Eat fresh fruit and veg Time restricted feeding (1pm-6pm), no snacking Skip junk, simple carbs, processed foods Skip drugs and alcohol Daily exercise Walk 5km 7x/week Lift weights 3x/week Run 5-10km 3x/week Sauna 5x/week Sleep (3-2-1 framework) No food 3 hours before bed No drinks 2 hours before bed No screens 1 hour before bed (e.g. read) Early to bed, early to rise And more obvious stuff like: low stress, low pollution, etc. ...
I was reading “The Art & Business Of Ghostwriting” by Nicolas Cole last night and was reminded of the rule of ones. The chapter was on the topic of “How To Niche Down As A Ghostwriter” and he describes a framework for niching down that involves 1 problem, 1 person, and 1 way. Here’s the quote: 1 Specific Problem: You can’t solve all problems for all people. Instead, you are much better off picking 1 Specific Problem and saying, “This is the only thing I do.” Why? Because when you specialize in solving 1 Specific Problem, you get to know how to solve that problem better than anyone else—which allows you to charge more (you’re the best, so you have the pricing power), and which allows you to create efficiencies for yourself (meaning you can do more work in less time). You get to be so good at solving this 1 Specific Problem that you can do it in your sleep. 1 Specific Person: When you get ultra-specific about who you help, and in what industry, three things happen. First, it’s exponentially easier for clients to find you (you aren’t a “window repair specialist,” you’re a “stained-glass window repair specialist”). Second, they immediately trust you (because you are saying, “I specialize in helping people exactly like YOU”). And third, because you only work with 1 Type Of Person, in 1 Specific Industry, you are going to know way more about the problems these people face, and the outcomes they value most—far more than all the other “I can write anything for anyone!” generalists. 1 Specific Way: Saying you specialize in solving 1 Specific Problem for 1 Specific Person is 90% of the game. But what pushes your offer as a ghostwriter over the edge (and makes people want to throw money at you) is by solving that 1 Specific Problem for that 1 Specific Person in a new, unique, and different way. I wrote about this in my book, Snow Leopard, explaining how the key to differentiating yourself is to solve Obvious problems in Non-Obvious ways, or to solve Non-Obvious problems in Obvious ways. It’s a good chapter, although could probably be condensed to one page (but shouldn’t). ...
After learning the basics of programming, we learn algorithms and data structures. I have very fond memories of implementing many algorithms and data structures in ANSI C and Java in the late 1990s. There was something very pleasurable in implementing well-known and well-defined computational concepts and then playing with them. Specifically, data structures like: arrays linked lists hash tables graphs stacks queues trees and on And algorithms like: binary search bubble sort quick sort heap sort breadth-first search depth-first search best-first search a-star search and on… I don’t think I’ve implemented any of these algorithms and data structures since. But there was a time in the late ‘90’s where that is all I was doing for months and months. Perhaps years. ...
I was thinking about LLM as a recommender system. I wrote about this the other day, how they can give a different type of recommendation. It occurs to me that we can use LLMs to give better recommendations. I want this for books. But, LLM recommendations are different how? That’s what I was thinking about. So, the most basic recommendations are: Other books by the author Other books in genre The most popular recommender systems for the last 15+ years are collaborative filtering. ...