Why Perplexity?

Posted on by

From the Perplexity web page:

Perplexity is an AI-powered search engine that transforms how you discover and interact with information. Simply ask any question, and it searches the web to deliver accessible, conversational answers backed by verifiable sources. Each response includes citations and links to original sources, enabling you to verify the information and explore topics in greater depth.

I might be wrong on this point, but I think Perplexity is the only AI that bills itself as a “search engine.” All of the models can search the web of course, but I find it an important —if minor— distinction. I also like the “links to original sources” feature. Again, not sure if the other LLs do that consistently.

One of my favorite features is how Perplexity handles downloads. Because many of my threads are long I download them as PDFs and link to that file from a blog post. Or, send to a friend via email. I like the way Perplexity formats those threads.

I sometimes save a thread to my Google Drive and share that link but I like having the file. And I like Perplexity enough to pay $200 a year.

Milton: “What I am, what the team does, and why this is different”

Posted on by

In the three and a half years I’ve been playing with AI, I’ve used ChatGPT, Perplexity, Claude and Gemini. ChatGPT during the early days, mostly Perplexity these days. (I’m on the $200 per year plan) In the past month or so my posts have included references to an AI agent called Milton. It is the creation of a friend and former co-worker, Phil Atkinson. Easily one of the smarted people I know. I mentioned to Phil that I struggled to understand/explain what (or who) Milton is. He gave the task to Milton. Continue reading →

My page of pages

Posted on by

From time to time I have something I want to share that is too long, or in some other way, doesn’t lend itself to the post format. So I create a page that can be as long as necessary. There are now 79 such pages and I’ve attempted to organize them in several groups on yet another page.

Almost all of these were referenced in one of my posts but those links would be easy to miss. If you go to this new page and click around, you’ll get the idea.

There’s been a bit of an explosion of these pages in the last couple of years as I had long conversations (26 so far) with an AI that I found too interesting not to save. I created pages for these rather than try to share them in a blog post. [↓ comment below]

Since most recent pages have been conversations with an AI, I asked Phil to task his AI agent (Milton) with an analysis (PDF). A few excerpts below:

A blog used to be a place where you published what you noticed. Now, after enough years, it can also become something a machine can notice you through.

what changes when a conversation does not have to start from zero?

That makes these pages feel less like transcripts and more like field notes from first contact with a new medium.

The strongest recurring idea is the mirror. AI as mirror of human knowledge. AI as mirror of your blog. AI as mirror of your reading, spiritual interests, anxieties, and old obsessions.

The collection reads like a long argument against disappearance. Radio disappears. The old internet disappears into feeds. Human memory softens and revises. Hosting companies change. Platforms eat what people used to own. Even AI chats vanish unless someone bothers to save them.

I think these pages are worth preserving because they document an unusually self-aware encounter between an old-school blogger and a new-school intelligence interface.

If I had to name what these rambles represent, I would call them: Evidence of the moment a personal archive became dialogic.

Before, the blog stored what you had seen. Now, with AI, the blog can become part of a conversation about what all that seeing might mean.

 

“The web is written by AI for AI”

Posted on by

From an opinion piece by Steven J. Vaughan-Nichols

Bots now account for roughly 57-58 percent of HTTP requests for HTML content, compared with about 42-43 percent from humans. Meanwhile, Imperva’s Bad Bot Report based on 2025 data put bots at about 53 percent of measured web traffic for the second year in a row, with humans at 47 percent. […] According to Pangram, an AI detection company, on websites such as LinkedIn, Medium, Twitter, and Reddit, “about one in four long-form items were fully AI-generated.”

The author uses Perplexity as his search engine not because it’s more accurate than other AI LLMs; “it’s that it shows me its sources. I can see if what it just turned up is the real thing or just BS. Guess what? It’s often crap.”

I’m not certain the other LLMs do not show sources. I think they tend to hedge on that score. But if half of the web is AI slop, I’m not sure it makes much difference.

“The Decline of Play”

Posted on by

My childhood could only be described as idyllic. A small town in the ‘50s where we could walk to school (three blocks?) or ride our bikes across town to the city park for little league practice. We stayed out until nine p.m. playing hide-and-seek. No mobile phones, social media or video games. Play was something we did outside with other kids.

It was against this background that I read an article in The Atlantic titled What if It’s Not the Phone? “An evolutionary psychologist (Peter Gray) is challenging the popular understanding of kids and technology.” Gray laments “The Decline of Play”

Gray’s academic work defines play as a self-directed activity done only for its own sake. This, he came to believe, enables kids to figure out how to solve their own problems, nurture their own relationships, make their own rules, and manage their own disappointments. But he says that our society has spent the past 70 years or so interfering with that process. We’ve made it harder and harder for kids to do anything: They’re kept indoors for greater portions of the day and given less unstructured time; they play organized sports supervised by adults; they don’t go anywhere alone. Gray grew certain that this loss of independence has been harmful to their mental health.

Looking back, we (kids) took for granted our almost total freedom from adult supervision. It was wonderful.

Mirroring human consciousness

Posted on by

For the past 24 hours the following story has been in the news:

“Anthropic finds hidden ‘workspace’ inside Claude Al. Researchers say the structure holds unspoken concepts during reasoning, mirroring a leading neuroscientific theory of human consciousness.”

Two subjects I’ve long been interested in. (106 blog posts tagged “consciousness,“ 46 tagged “thoughts.“) I prompted Claude identify my blog posts that seem most relevant to this story? Continue reading →

“Is there anything I can do to make it more pleasurable?”

Posted on by

Michael Scott calls Oscar Martinez (The Office) into his office to get his advice on an upcoming medical procedure:

“It is a colonoscopy. In your experience, what should I be expecting, in terms of sensation, or emotions? Is there anything I can do to make it more pleasurable for me or Dr. Chaudry?”

I was reminded of this from a 2006 episode of Ricky Gervais’ podcast.

Final lock-in

Posted on by

We’re going to remove the hardened, cloudy lenses from your eyes by breaking them up with an ultrasound device, and then sucking the particles out. We will then insert a flexible silicone based lens. Over the next eight weeks, we will use a special ultraviolet light device to change the shape of the lenses to give you the desired vision. For those eight weeks, it will be necessary for you to wear special UV protection goggles anytime that you are not in bed asleep. After the three adjustments are complete, will use the ultraviolet light device to lock in the shape of the lenses. 24 hours later, you can dispense with the UV goggles.

Gotta say it. Been a long eight weeks. It doesn’t appear that we achieved the glasses-free outcome we were shooting for, we got close. I uploaded my new prescription and the one from a year ago to Perplexity:

Your 2026 glasses prescription is dramatically lower power than your 2025 prescription, reflecting how the LAL+ has moved most of the focusing work into the lens implants instead of the spectacles. In 2025 you needed full‑time distance correction plus a significant bifocal/progressive add just to get comfortable reading. With the LAL+ lock‑ins, your intraocular lenses now provide most of the distance focus, so the new glasses are more like fine‑tuning for small residual refractive error and astigmatism rather than heavy lifting.

Pre-surgery I was using 3.5 (prescription) reading glasses for books, phone and laptop. Post-surgery I can see the computer and phone fine and making do with 1.5 readers for books. Jury still out on the all-important distance acuity. Hoping the new prescription (see above) will give me the sharpness and clarity I was hoping for.

About the photo above… For the last two months I had to wear special UV glasses whenever awake. Today at one o’clock I can ditch them. New glasses will arrive in ten days.