Dave Jimison shares the idea of asking your LLM how you communicate with the prompt:

Review the way I’ve communicated with you across our past conversations and give me an honest, direct assessment of my communication style with AI. Tell me how I express dissatisfaction, how I tend to work through conflict or disappointment, how I give positive feedback, and what strengths, blind spots, or recurring patterns you notice in how I collaborate with AI.

I got a lengthy analysis from Claude Code. Here are some highlights:

How you express dissatisfaction

Blunt, factual, and almost never emotional. Across 1,345 messages there is no profanity, no sarcasm, and the strongest emotion on record is “ugh.” Your dissatisfaction has a consistent anatomy: name the mismatch, then supply the missing fact or the intended mental model.

I’m pretty sure I’ve written fewer than a handful of profane words to AI before. It certainly wasn’t when using Claude Code. It’s usually in response to something that was surprising. It doesn’t make sense to me to use profanity or sarcasm with an LLM. Doing so feels like anthropomorphising the agent.

The overall shape: you run AI like a staff engineer runs a team — high-trust delegation inside an explicitly constrained envelope, mandatory personal review at the reputational boundary, adversarial review as a habit, and a deliberate teach-the-agent loop that turns every correction into a durable rule. The through-line of both your strengths and your blind spots is the same trait: you optimize for keystroke economy and trust the machine to hold state. When the state-holding works, you’re an unusually effective collaborator; when it doesn’t, that’s where every cycle you lose comes from.

Interesting learnings, and nothing surprising for me here. I think I’m pretty deliberate in thinking like an engineer when using AI agents. I understand the harness is keeping memory, and I use it to make sure I’m not repeating myself (too often). But I can see that I can sometimes lean too much on the agent’s memory and state, so it’s important for me to know (or more likely intuit and feel) the limits of the agent.

Unauthorized Wi-Fi network found on Delta flight after DEF CON:

Delta Flight 591 was traveling from Las Vegas to Atlanta on Aug. 10 when an unauthorized Wi-Fi network was detected aboard the Boeing 757. […] Messages attributed to the flight crew indicate there were concerns that someone aboard the plane had created a network called “Delta WiFi Fast.”

Sounds like someone was playing with their new Pineapple after buying it at DEFCON.

I’ve added a new type of blog post to Ivan: Thinking called “Musings” which are essentially tweets or status updates. These are also known as microblog posts, and, for me, the big thing about them is that they don’t require me to think of a title for my posts.

I’ve been off of using social media for over a decade, but I’ve more recently had the itch to throw my words out into the void again. I prefer to microblog from my phone, so I have a custom iOS app that I jot down some ideas in, and I publish by committing directly to my site repo. This lets me post from the sofa, the car, and… yes… the pooper.

Beware! Expect more random musings from me.

From The Session You Cannot Take With You:

A user should be able to close an account, keep a session, and hand it to another model. The new model may disagree, ask questions, or perform worse. It should not be staring at ciphertext where the old model saw the user’s history, evidence, plans, and delegated work.

Agreed, and relevant to folks running local models. I want to be able to swap between different models as needed, but it seems like session context is being hidden by model providers who don’t make that easy.

Had a great chat with Josh Nguyen today. He’s working on RoverAI, doing super interesting work with local LLMs. I think more and more people and businesses will care about how much data we keep feeding model providers. I know I’m concerned about it, and I don’t think I’m alone. Beyond the privacy concern, having personal context available to models is a huge win too.

I don’t really want Claude to have all that data about me: how can I trust that they’re not using it to advertise to me or manipulate responses? Take them at their word?

I want to run my models locally where I control who gets to see my data, and it’s clear that the model is working for me rather than for a model provider.

Limited Edition Jonathan (via) thinks Apple is the king of AI.

I’ve been running my own local model and agent on an M4 Max with 128GB RAM. There’s a certain wow factor when running a local model the first time and realizing a file gives me access to all of human knowledge (OK, I know that’s not entirely accurate and overly simplistic, but the feeling is still valid IMO).

I’ve been using Hermes Agent against Qwen3.6-35B-A3B-4bit. It’s no Fable or Opus, but it does let me ask questions about parenting or health that I don’t feel comfortable asking Claude about. I’m not sure if other folks care as much as I do about the privacy concerns of throwing so much private details of our lives at these LLM providers. It does look like Apple is throwing their weight behind the worldview that having a Personal AI that lives on our devices is the way to go. It means they’ll make hardware powerful enough to run these models.

It’s still pretty early days of running local models, and I’ve yet to try out Apple’s latest with iOS/macOS 27. My own setup feels pretty rudimentary, but I can see it improving over time.

I recently came upon the term poke-yoke:

Any mechanism in a process that helps an equipment operator avoid mistakes and defects by preventing, correcting, or drawing attention to human errors as they occur. It is a Japanese term that means “mistake-proofing” or “error prevention”, and is also sometimes referred to as a forcing function or a behavior-shaping constraint.

In my mind, typed programming languages are a kind of poka-yoke. Using data structures for constraints is a poka-yoke. Modals and interstitials can be poka-yoke.

I think I already use this concept in my UX designs often, just didn’t have a term for it.

Aleem Shaun (via) has been a longtime Day One journaler.

I’ve used Day One for more than a decade. It was an excellent journalling app. Private, minimal, easy to use, with excellent features such as geolocation, weather, ‘On this Day’, and book printing. Features that got out of the way and either worked quietly in the background or appeared only when you summoned them. That’s changed.

He’s been getting frustrated with Day One forcing the AI chat feature down his throat without a way to remove it. As he looks for alternatives:

The features I will most miss are On This Day and book printing. I can replicate On This Day with shortcuts and widgets. I’ve also been using Flohgro’s excellent On This Day Rewind App. Book printing, which I use to curate personal memories for my kids, will be a bigger pain point and harder to replace. My research hasn’t turned up much. I’ve looked at Blurb, Momento and others. None fully replicate what Day One does natively.

Looks like the young folks are getting into birding.

The article mentions 2 reasons:

• COVID: an easy activity to do outside of the house that was low stress/screen and I’m guessing cheap too
• new birding tech like the Merlin app.

It’s not just for the old retired folks, yo.

Walking around the streets of Kyoto last week, in the sweltering heat of mid-summer Japan, the familiar sound of crickets filled my ears.

It brings me a sense of nostalgia.

Of my youth. Of a carefree time. Of staying up late to watch anime on my CRT.

懐かしいな。

Neal Stephenson’s writing, to me, often has a sense of condescension to it. It was off-putting to me when I read Cryptonomicon, but when I read his recent post, Writing by Hand is Good for your Brain - Here’s how to do it, I was delighted at his unspoken jabs at the current zeitgeist of our obsession with AI.

Every so often, when I’m signing books at a book tour appearance, someone will come up to me and say something like “you must have writer’s cramp!” or “is your hand sore yet?” I never have the time to provide a full answer. If I did, however, my answer would be that never, at any time during a quarter of a century during which I have spent a substantial fraction of each working day writing by hand, have I experienced even the faintest traces of so-called “writer’s cramp” or any other such hobgoblins.

In his section titled Don’t use a gadget *cough*, he writes:

Too much friction, and too little friction, are both more tiring than just a little bit of friction, and that’s the balance that is reflected in the fountain pen/paper technology.

Interestingly…

Since I do a lot of work from one location, I have a corner of a tabletop set up there with ink bottles and a folded-up paper towel for wiping off the nib after it’s filled (I have been using the same paper towel for about twenty years).

Did I read that part right? He’s using the same piece of paper towel for 20 years? WAT?

My own setup:

• Moleskine notebooks
• Papermate Flair pens, which are felt tipped rather than gel tipped… hmm, I’m gonna try out the Pilot G-2’s and see how that goes.

Debugging a crash on the new Little Memory 2.0 app today, and found a crash report with the termination code: 0xdead10cc. Interesting hex code, or rather, hexspeak. Seems there’s some fun Apple’s done with termination codes:

• 0xdead10cc - “dead lock” - an application holds on to a system resource while running in the background
• 0x8badf00d — “ate bad food” — the watchdog kill for blocking the main thread too long at launch/resume
• 0xc00010ff — “cool off” — killed for thermal pressure
• 0xdeadfa11 — “dead fall” — user force-quit an unresponsive app
• 0xbad22222 - “bad too repeatedly” - a VoIP application has been terminated by iOS because it resumed too frequently
• 0xbaaaaaad — “baaaaad” - the log is a stackshot of the entire system, not a crash report
• 0xdeadfeed - “dead feed” - crash when a timeout occurs spawning a service

In Kyoto, the Gion (祇園) district is the old entertainment area of town. In my mind, it’s the place where tourists would go to try to get a glimpse of a geisha or, more likely, a maiko. There’s the famous Gion Matsuri that’s one of the largest festivals in Japan every year.

Something I didn’t know until looking it up today was that the word Gion is derived from the Buddhist term Jetavana:

Jetavana was the place where the Buddha gave the majority of his teachings and discourses

In Chinese, Jetavana is spelled 祇樹給孤獨園, and that long name got abbreviated into just the first and last characters: 祇園 (Gion).

The main shrine in Gion was originally called Gion Shrine (祇園社 or 祇園神社). During the Meiji era, Buddhism was a four-letter word, so the shrine got renamed to Yasaka Shrine (八坂神社), which stuck, but the neighborhood still kept being called Gion. And thus, we have the Gion district with the Yasaka shrine.

We’ll be in Japan soon, in Kyoto, Osaka, and Tokyo. Even though I lived in Kyoto, I feel like I didn’t do as much exploring of Osaka, and, of course, there’s always more to see. A friend recently told me about Namba Yasaka Shrine, which is a shrine shaped like a giant lion’s head.

The lion is said to swallow evil spirits and warding off bad luck with success in exams, business, and competition.

Oh, boy, looking forward to checking this one out while we’re in town.