An Inadequate AI Solution

Let’s take the example of printers, which tend to suck. Here is one example of suckage at work, and the instructive hell it put me through:

The Canon MG3600 is my wife’s. It sits by her desk and does a good-enough job.

The Epson WF-3520 is mine. It sits by my desk and leaks black ink. It has been doing that since I bought it in a hurry for $35 at a Goodwill store when we first got to town in the summer of ’21. The drip runs at about a drop per month, but otherwise it’s been okay. I use it mostly for scanning. It’s good at that.

Or was, until I encountered the problem above.

Answers to questions about the error code proved fruitless in a series of searches (such as this one) and at the Epspon link above.

So, naturally, I went shopping for a new printer. My only requirement was that it would scan at least as well as this old Epson.

Alas, scanning is a checkbox for “all-in-one” printers. Here’s an example from PC Magaziine. Nothing much about scanning. This makes sense, because demand for high-quality scanning is relatively low, and most printers are at least okay at it. But Consumer Reports (bless them) does rank scanning quality, and it gave me this in reply to an Ask CR question:

The Canon PIXMA G3262 is not one of CR’s recommended printers, rating a middling 47 out of a possible 100 score. Its problem areas are low predicted reliability, low versatility, and slow text speed. The only thing it’s good at is scanning. The printer page on Amazon is also not encouraging. It has only two user ratings, and both call it junk.

The Brother MFC‐L8905CDW is $699.99 at Amazon, which is way out of my range.

The Canon Pixma MG7720 is now in the used market, and (far as I can tell) available only on eBay, and none of the offerings there look interesting.

So I went looking just for scanners, and narrowed my choice down to the Canon CanoScan Lide 400, which is just $78.86 on Amazon. I put it in my cart, then I thought, Wait a minute. What if I asked an AI what that error code means?

So I did, with ChatGPT. The dialog:

Me:

What does “Failed to open connection to device (-21345)” mean on a Macbook Pro running Sequoia 15.3.1 that is trying to connect to an Epson WF-3520 printer?

ChatGPT:

“Failed to open a connection to the device (-21345)” on your MacBook Pro running macOS Sequoia 15.3.1, when attempting to connect to an Epson WF-3520 printer, typically indicates a communication issue between your Mac and the printer, particularly affecting scanning functionality. Here’s how you can troubleshoot and resolve this issue:

Step-by-Step Solutions
1. Enable Local Network Access for the Printer/Scanner
macOS Sequoia introduces enhanced privacy settings that may block devices from accessing the local network. To ensure your Epson WF-3520 has the necessary permissions:​

Navigate to System Settings.Select Privacy & Security.Click on Local Network.Locate your printer or scanner in the list and ensure it’s toggled on.​
Apple Support Community
Reddit

This step has resolved similar issues for many users experiencing the (-21345) error.

It listed other solutions, but that one worked. Three levels down in System Settings, the printer had been toggled off, presumably by Sequoia’s enhanced privacy settings. I am now back to scanning normally with my lousy old Epson.

I could take my learnings here in at least two directions:

I could carp about Apple failing to tell customers about potential hassles created by enhanced privacy settings. Ask ChatGPT “What kinds of things do Apple’s enhanced privacy settings (introduced with Sequoia) break or at least inconvenience?” and you’ll get a long list of answers, starting with the one I encountered with the printer. To my knowledge (always subject to correction), Apple hasn’t bothered with the same. (Wouldn’t providing customers with that kind of list be nice work for Apple Intelligence, which so far is an embarrassing fail?)I could compare how ChatGPT, Claude, Gemini, Meta, CoPilot, Perplexity, and other early AI leaders perform on challenges like this one, but that would be a waste of time. That’s because, for all the good they do, they are not ours.

See, AIs of the usual sort don’t know anything more about our personal stuff than we tell them, and we may not want to do that, just for privacy reasons. Also, they tend to forget. And they are not ours. At best they are personalized, rather than personal.

A truly personal AI (or pAI) would be all mine and trained on what is under my control. For example, all my property, including these two printers. It would have data about my purchase and use of these printers. But it would also have access to data about identical or similar printers out in the world, and ways to engage the corporate AIs so we could solve problems together in far better ways than what we have now. In the process, the likes of Epson would have better intelligence about product usage than they’re getting now.

So we are talking here about agent-to-agent stuff, with the right capabilities and resources located in the right places.

Toward making that happen, there was lots of talk earlier this month at IIW XL (our 40th in 20 years) about MCP (the Model Context Protocol), A2A (agent-to-agent protocol), and GNAP (Grant Negotiation and Authorization Protocol), all of which hold promise. I’m not here to debate or advocate any of them, just to note that there are protocols out there, as options with which we can work.

But what about the entities using those agents—companies making and selling products on one side, and customers using those products on the other? How can they learn from each other, and not just make transactions and then get frustrated with each other when problems show up?

One answer is Market Intelligence That Flows Both Ways. I wrote that in 2016: nine years ahead of its time, so far.

Looking back, I don’t think that kind of flow will happen without AI agents, and full agency by those agents operators, on both sides.

We need to be able to lead in our dances with companies in the open marketplace. But first, we need personal AI to help us gather and manage intel about our lives, our things, our relationships (including the medical and financial kind), our travels, and the services we use. We are not close to having any of that, and not helped by the Apples, Microsofts, Amazons, and Googles of the world, all of which want to confine our capacities to their walled gardens.

We don’t need to knock the walls of those gardens down. The revolution we need will simply obsolesce them.

That’s why it will not be supplied by APIs, or by anything that requires that we have an account. We need to be independent and self-sovereign: first parties who speak for themselves in first-person voices.

I’ll say more about all that in my next post and others to follow.