AI advancement has had roughly four eras. They’re about 20 years apart, last a few years, but have an “AI Winter” in between If we want credible attempts to create AGI … then we need at least the next, due around 2065. Maybe 2095. Ignore the Hype Start learning to use it now. Start with… Continue reading Hedgewitch Part 8: Coda
Hedgewitch Part 7: Oh, and it’s in a Bubble
If they’re big enough, every fad turns into a bubble. Actually every fad does, but the little ones are hard to see. Currently the Fad is “Use LLMs for Everything” It starts with a discovery or invention, and zooms to a peak that it can’t possibly deliver on. Then it fails to do something it… Continue reading Hedgewitch Part 7: Oh, and it’s in a Bubble
Hedgewitch Part 6: What would Dave like me to Say?
LLMs constantly make errors. Why? Answering the wrong question is the first underlying problem. Phrased in polite Canadian, an LLM always answers the question “what would a reply to this look like?” In less polite language, it asks “What would Dave like to hear?” The US and business term? Suckup. If all your subordinates suck… Continue reading Hedgewitch Part 6: What would Dave like me to Say?
Hedgewitch Part 5: Upsy-Daisy!
Using it for what it’s good at was an obvious approach. Turning it upside-down was good. What About a Little Kid? Treating it like a little kid and walking it through something, like a math problem, also looks promising. I wanted to draw a particular mathematical figure. So I told the three-year old to 1.… Continue reading Hedgewitch Part 5: Upsy-Daisy!
Hedgewitch Part 4: What’s Wrong?
In Part 1, I said I used LLMs “upside down”, not the way the (now well-cooked) wizard did in Torches and Pitchforks. Implicitly I’m saying that way is wrong. Where’s my Proof? A missing flood of new AI-written programs. That’s the obvious case: I should be seeing a flood of highly-visible, customer-facing phone apps. I’m not.… Continue reading Hedgewitch Part 4: What’s Wrong?
Hedgewitch Part 3: LLMs Should Challenge, Not Obey
Most people treat LLMs like an obedient secretary. I treat them like lint — a fallible tool that suggests mistakes I made, ones I evaluate for myself. I stole the entire idea from Advait Sarkar. It was in the October 2024 Communications of the Association For Computing Machinery. LLMs: spot errors easily, write really bland… Continue reading Hedgewitch Part 3: LLMs Should Challenge, Not Obey
Hedgewitch 2: My Favorite Errors
I have some bad habits I speak in run-on sentences never get to the point. I don’t mind that in speech, but it’s not good in writing. So I need to do something about it if I want to learn how to be a better writer. So I started with the low-hanging fruit: teaching me… Continue reading Hedgewitch 2: My Favorite Errors
Hedgewitch Part 1: LLMs
I’m a systems programmer and published author. I’m a heavy user of LLMs. But not one word of my books were written by LLMs, and not one production program. So what could I possibly be using them for? To teach me to to write and program better, even though they write and program “unimpressively” I’m… Continue reading Hedgewitch Part 1: LLMs
Torches and Pitchforks
The peasants are encircling the palace, with torches and pitchforks The king is a 3-year-old who's memory has been stuffed with every book ever written (on vellum, this is from a while ago). But they're a three-year old. They babble incessantly: about animal husbandry, in the middle of a city. They don't know true from… Continue reading Torches and Pitchforks
Light Phone
Want a phone you can give to a little kid you're still requiring use the net under family supervision? Got one! The minimalist Light Phone teams up with Andrew Yang’s Noble Mobile, which pays you to stop doom-scrolling[1] - https://techcrunch.com/2026/05/19/the-minimalist-light-phone-teams-up-with-andrew-yangs-noble-mobile-which-pays-you-to-stop-doomscrolling/ The Light Phone offers a middle ground between a hyperconnected iPhone and a clunky flip… Continue reading Light Phone
This Blog has No Leaves 