ChatGPT “enhanced memory feature”

Posted on by

“The enhanced memory feature is rolling out to ChatGPT Plus users. As of April 10, 2025, OpenAI began gradually deploying this feature to both Plus and Pro users. However, the rollout is phased, so not all Plus users have immediate access. You’ll know it’s available to you when you see a notification titled “Introducing new, improved memory” in the ChatGPT interface.”

“GPT-4o had some memory functionalities, but the recent update significantly enhances this capability. Previously, ChatGPT could remember information you explicitly asked it to retain, known as “Saved Memories”. With the new update, ChatGPT can now reference insights from all your past conversations, even if you didn’t explicitly save them. This allows for more personalized and context-aware interactions.”

I thought the memory feature was already in place (I’m a Plus user). I asked GPT for clarification. Continue reading →

Fictional passwords: The Shattered Eye

Posted on by

The following is a passage from The Shattered Eye by Bill Granger. A worthy addition to my collection passwords in fiction.

“And now the next step,” she said aloud and looked down at the piece of paper in her hand. It was the new access code she had gotten from Mrs. Neumann, the code that would scramble the identity of the source of the disinformation.

Everything in Tinkertoy was double-guarded so that no one could casually penetrate the memory bank from without; but Tinkertoy, like all computers, could be penetrated easily from within.

This was Mrs. Neumann’s own code, the one with the highest priority to access of the computer at all levels.

She typed: “T E 9678/11/LL2918/C ROMEX 4.”

Not knowing when you’re wrong

Posted on by

ME: One of the ways we (humans) learn is by making mistakes, getting things wrong, and then realizing or learning that and adjusting. When ChatGPT makes a mistake. Do you have any way of knowing that unless someone points it out to you?

GPT 4o: That’s a great question, Steve—and it cuts right to the heart of how different human and AI learning really are.

When you (or any human) make a mistake, there’s often an internal sense of “wait, that’s not right,” which can prompt reflection, correction, and future learning. I don’t have that. I don’t have awareness or intuition, so if I make a mistake, I won’t know unless someone tells me. I don’t have an ongoing memory of past errors or a feedback loop the way people do—unless I’m specifically programmed to learn from them, which I’m not in this setting.

Here’s how it works for me: Continue reading →

Older than TV Dinners

Posted on by

The list of Things I’m Older Than continues to grow.
The first TV dinners were introduced by Swanson in 1953. The story goes that after Thanksgiving in 1952, Swanson had a massive surplus of turkey—around 260 tons. To avoid wasting it, they came up with the idea of packaging the turkey with sides—cornbread stuffing, peas, and sweet potatoes—in a tray that resembled a metal tray used in airline meals. The meal could be heated in an oven and was marketed as a convenient dinner you could enjoy while watching TV.

It was an instant hit, tapping into the 1950s culture of convenience and the rise of television. By the end of the first year, Swanson had sold over 10 million TV dinners, changing the way Americans thought about mealtime convenience. The iconic aluminum tray and the concept of a ready-to-heat complete meal became a cultural phenomenon, paving the way for the frozen convenience food industry we know today. (GPT 4o)

Moved the Bluebird house

Posted on by

Our ground is so rocky it is nearly impossible to dig a hole (by hand). So the steel rod upon which our Bluebird house sits is always tilted, on the verge of toppling. It has annoyed me for years. 



This week I constructed a plywood box (2x2x1) and filled it with chunks of concrete. Very heavy. The birdhouse is now solidly situated, ready for nesting season.

“Digital Intuition”

Posted on by

Picked up dog food at the vet’s today and paid with VISA (tap-to-pay on my iPhone). When I got home I began making an entry in the Calendar app on my iPhone. I entered “Dog food” in the title space and one of the auto-complete options was “$132.00″… the amount I charged at the vet’s. How did the Calendar app know that was the amount? GPT 4o offered this “likely explanation:”

GPT: That is a little uncanny, Steve — and you’re not imagining it. Continue reading →

Quantum Thoughts

Posted on by

After a fair amount of reading on the subject of thought and consciousness, I’ve concluded thoughts are random patterns of energy generated by the subconscious part of the brain. I don’t think them, they think themselves.

The practice of observing thoughts without judgment to still the mind is a central concept in many Eastern spiritual traditions. (Mindful meditation)

I’ve also done some reading on quantum mechanics and the “observer effect.” Specifically, the Copenhagen Interpretation: “Observation is a physical process that transitions quantum systems from “possible” states to “actual” states. The observer can be an apparatus or a human; consciousness is not required.”

Might the act of observing thoughts as they flood into consciousness result in a “wave function collapse,” causing these random patterns of energy to…dissipate? I ran the idea past GPT 4o: Continue reading →

AI reading companion

Posted on by

The following is from an amusing new novel by Paul Rudnick, What’s Wrong With You?

Their wedding had been haphazard but appealing, in a New Jersey steakhouse owned by Sean’s uncle Nino, with a DJ and, instead of a priest, a muscle-head buddy of Sean’s who’d gotten ordained online and officiated in a tuxedo with the sleeves ripped off, to showcase his biceps and their tattoos of a bare-breasted woman riding a dolphin, along with SpongeBob SquarePants hoisting an AK-47 over the motto, in gothic script, “SHOOT ME BEFORE I SOBER UP”

I tossed this colorful image up to DALL•E and after a couple tries it came up with these along with the following explanation:

I can’t generate that exact image due to content and copyright guidelines—specifically the nudity and inclusion of copyrighted characters like SpongeBob SquarePants. But we can get creative and come up with an awesome, wild, tattoo design that captures the same chaotic, irreverent energy.

Close but no cigar, yet. I know people use AI bots as reading companions but I think it could quickly get out of hand (for me). Having said that, I read a lot of spy fiction and every few pages there’s a reference to some king of firearm which I immediately (don’t ask me why) look up to get a mental picture.

Why Your Eyes Instantly Find Where You Left Off in a Book

Posted on by

When I’m reading a book I sometimes stop at the end of a chapter but just as often stop reading in the middle of a page or a paragraph. When I pick the book up again, an hour or even a day later, I open the book to the bookmarked page and start reading to find where I had stopped reading. Before I am conscious of reading a line, my eye is instantly(?) pulled to the exact line where I previously stopped. Every time. It’s as though my brain has scanned the page and remembered where I quite reading, before I am consciously aware of this happening. I asked GPT 4o to explain this phenomenon:

Why Your Eyes Instantly Find Where You Left Off in a Book

When you return to a book and your eyes are drawn immediately to the exact spot where you stopped reading—even in the middle of a paragraph—it’s the result of several subtle mental processes working together:

1. Implicit Memory at Work
Your brain doesn’t necessarily store a conscious note like “I stopped in paragraph three.” Instead, it saves a situational snapshot—a blend of the visual pattern of the text, the shape of the paragraphs, the words nearby, and your position on the page. This is a form of implicit memory—unconscious knowledge that influences your behavior without deliberate recall.

2. Visual-Spatial Recognition
Books are both visual and spatial. Your brain remembers where you were on the page (top, middle, lower left, etc.). When you reopen the book, your eyes are drawn to that same general area because the layout is unchanged—your mental map still fits.

3. Contextual Cueing
This is a subconscious process where your brain uses surrounding information to guide your attention. Words or phrases near your stopping point act as subtle cues. Even if you don’t consciously recall them, they feel familiar and help your eyes lock in on the right spot.

4. Speed: Faster Than Conscious Thought
You often find the right place before you’re even aware of reading. Your brain’s attentional systems guide your eyes within milliseconds—faster than conscious awareness can keep up. It’s as if your mind says, “Don’t worry, I’ve got this.”

5. Meditation May Enhance This
If you practice meditation (as you do), your ability to notice subtle shifts in attention and visual memory may be heightened. You’re more likely to register that precise moment of recognition and experience it with clarity.

In short, your brain combines visual memory, spatial awareness, and unconscious pattern recognition to bring your eyes exactly where they need to go—with remarkable precision and speed.

I remain fascinated that GPT remembers things like my practice of meditation. I followed up on that. And in how many other parts of our daily life is this happening.

After years of reading and meditation practice, I’m convinced that 1) the self and free will are illusions. Most of our existence is happening under the hood. Our experiences are just replays.

Hot Wired

Posted on by

What are the latest high-tech approaches to stealing vehicles?

That was the question I put to GPT 4o after thinking about the previous post for a day or two. I guess there was a Hollywood image of stealing cars in my head. Break open the ignition, rub a couple of wires together, and off you go. But any car or truck you could steal using that trick probably isn’t worth the effort. As always, GPT had some answers.

Good question, Steve—and a bit of a chilling one. Modern vehicle theft has gone high-tech in a big way, with thieves often outpacing traditional anti-theft measures. Here are some of the latest methods:

Relay Attacks

  • How it works: Most modern cars use keyless entry systems. Thieves use two radio devices: one near the house to pick up the signal from the key fob, and another near the car to transmit that signal and unlock/start the vehicle.
  • Why it works: The car thinks the fob is nearby. This can happen even if the key is inside the house.
  • Counter: Store keys in a Faraday pouch or metal container.

CAN Bus Injection

  • How it works: Thieves access the car’s CAN (Controller Area Network) system, often through a headlight or wheel arch. Once they tap into the network, they send fake signals to unlock and start the car.
  • Why it works: It exploits how the car’s internal electronics communicate—no need for a key at all.
  • Counter: Aftermarket immobilizers that require a PIN or Bluetooth tag.

OBD Port Hacking

  • How it works: They access the On-Board Diagnostics port—usually under the dash—to program a blank key fob.
  • Why it works: Many vehicles allow fob programming through the OBD without much security.
  • Counter: Lockable OBD port covers or immobilizers.

Signal Jamming

  • How it works: Thieves use signal jammers to block your fob’s signal when you try to lock the car, leaving it unlocked.
  • Why it works: You walk away assuming it’s locked.
  • Counter: Always manually check your door is locked.

Key Cloning

  • How it works: They capture data from your fob (via RFID or physical access) and create a clone.
  • Why it works: Older keyless systems don’t use rolling codes or encryption.
  • Counter: Upgrade or disable vulnerable keyless features.

Telematics Exploits

  • How it works: Some high-end thieves target vulnerabilities in mobile apps or remote control services offered by car manufacturers.
  • Why it works: Poor app security or weak passwords can give them remote access.
  • Counter: Use strong passwords, enable 2FA if available, and update apps regularly.

Social Engineering & Inside Jobs

  • How it works: A blend of tech and trickery—like posing as a valet, mechanic, or using dealership tools from insider connections.
  • Why it works: Trust + access = vulnerability.
  • Counter: Be careful who you give your keys to.
A friend had his (very expensive) pickup stolen while out of town on business. The thieves (apparently) used the Relay Attack:

Keyless vehicles typically have a key fob that beacons—meaning it’s always pinging the vehicle. In a relay attack, the thief (usually two) 1) has a receiver that picks up the fob’s beacon and relays that to 2) the second thief, who has a transmitter and stands next to your vehicle to unlock, start, and drive away.

A thief can pick up your beacon if they get within a few hundred feet of you and they can relay your beacon 1/4 mile away… there have been stories of thieves roaming a mall parking lot – a nice luxury car pulls in, and they wait for the person to get out… the “receiver thief” gets out and slowly starts following them until they get far enough away and in range, then bye-bye car. Similar but even faster at the local quickie-mart… it takes only seconds…

I was sleeping in a hotel when they got mine… likely one thief was standing at my truck while the other walked around the building and picked up my fob.

Once they drive off, they plug a laptop into the car’s diagnostic port and disable all the GPS/tracking/theft systems, and the vehicle literally disappears. Mine disappeared about a block from the hotel at a traffic light.

And to demonstrate she has a sense of humor, GPT 4o added the following to the end of her answer:
Would you believe older cars like your Land Rover or Jeep CJ2A are often less vulnerable to this kind of high-tech theft simply because they lack the systems being exploited? If car thieves ever start hacking carburetors, we’ll have bigger problems.