Linked List: July 8, 2026

Wednesday, 8 July 2026

‘PARRY Encounters the DOCTOR’ – Chatbot on Chatbot Action Circa 1973 ★

Back in the primordial days of AI, PARRY was an ELIZA-style chatbot created by psychiatrist Kenneth Colby to simulate the words of a paranoid schizophrenic. Someone had the genius idea to connect it to ELIZA (a.k.a. “DOCTOR”). Vint Cerf published the transcript as an RFC in 1973, and I laughed my ass off reading it. A taste:

Do you know anything about bookies?

What makes you think I know anything about bookies?

A bookie didn’t pay me off once.

What does that suggest to you?

I beat up the bookie who did not pay off, and I thought he might use his friends in the underworld to get even with me.

What else would you like to discuss?

What do you know about racketeers?

Vint Cerf, by the way, retired from Google last week at the spry age of 83.

Mac Apps Can Escape From Squircle Jail If They’re Not in the Mac App Store ★

Tyler Hall:

We all know about macOS Tahoe’s terrible app icons and how 3rd party developers have been confined to squircle jail.

If you’re lucky enough to distribute an app outside the Mac App Store, you can break free of squircle jail using NSDockTilePlugIn. It’s not strictly the intended use-case of that API. And it’s not allowed in the Mac App Store, either. But it can solve the problem.

So today’s release of Iris adds three additional app icons to choose from in the app’s Special ~~Preferences~~ Settings pane. And since they use the NSDockTilePlugIn API, the custom icon remains even when you quit the app.

Iris is far from the only app using this or other techniques to sort-of escape squircle jail. All the apps I’m aware of doing something like this are Mac-assed apps. It’s a good litmus test.

‘Searching for SmarterChild’ Kickstarter ★

After reading my posts earlier today about ELIZA, the first “hit” chatbot from the 1960s, DF reader AP sent me a link to the Kickstarter page for Searching for SmarterChild, a project from documentary filmmakers Lindsey Sitz and Zan Gillies to make a movie about SmarterChild, an AOL Instant Messenger chatbot that once had 30 million “friends” (a.k.a. users). I don’t recall ever hearing of SmarterChild before, let alone using it. (I think I was on a very different level of the Internet back then.)

But this looks like a great indie nerd documentary. The Kickstarter campaign has just one week left and they’re a wee bit short of their primary goal, and quite a bit short of their stretch goals. I just chipped in.

My Conversation With ELIZA ★

I vaguely recall first trying some version of ELIZA back in the 1990s. I never found it all that impressive nor understood its stature in the AI literature. It’s better than a bunch of if/then statements but not by much. There’s some natural language grammar parsing that is somewhat interesting, but I never thought it came close to passing the Turing Test, and I was always skeptical of claims that people got deeply involved with it as a virtual therapist/counselor. I just tried it again, via The ELIZA Archeology Team’s web-based re-creation. Here’s my transcript:

HOW DO YOU DO. PLEASE TELL ME YOUR PROBLEM

I don’t really have a problem.

DON’T YOU REALLY REALLY HAVE A PROBLEM

No.

ARE YOU SAYING ‘NO’ JUST TO BE NEGATIVE

No.

YOU ARE BEING A BIT NEGATIVE

No.

WHY NOT

I’m just being honest.

IS IT BECAUSE YOU ARE JUST BEING HONEST THAT YOU CAME TO ME

No, I’m just curious to try this out.

WHY ‘NO’

I said “no” because my “just being honest” is not the reason I came to you.

YOUR JUST BEING HONEST IS NOT THE REASON YOU CAME TO I

That’s ungrammatical.

I AM NOT SURE I UNDERSTAND YOU FULLY

I am quite sure you don’t.

HOW LONG HAVE YOU BEEN QUITE SURE I DON’T

Pretty much since I got here.

There’s something wrong with people who consider today’s chatbots to be their friends or companions. But there’s something really wrong with people who considered ELIZA a useful confidant. Like suffered-a-severe-head-injury wrong.

The ELIZA Archaeology Project ★

The ELIZA Archaeology Project:

ELIZA is the original and highly influential chatbot that launched the genre of human-computer interactions using text-based agents. It was created at MIT in the 1960s as part of Project MAC by it’s [sic] designer and programmer, Joseph Weizenbaum. ELIZA not only allowed Weizenbaum to develop a mode of interaction with computers that is highly interactive, it also contributed to the way in which people were starting to conceptualize computers as having the capacity to usefully engage in conversation. You can try an accurate reimplementation of ELIZA developed as part of this project.

We plan to contextualize the program, offering its history and context as well as offering a detailed explanation of how the code works. This project will look at the culture of programming in which Weizenbaum was working and then explore his turn from ELIZA/DOCTOR, as he began to warn of the hazards of treating machines like humans. We will look at later works inspired by ELIZA and consider its influences on the way talking computer programs are represented in literature and film.

Via Jason Kottke, who also links to an upcoming book from the same team.

Their blog has an entry that discusses something I’ve been meaning to link to for a while, regarding Weizenbaum’s secretary:

Nonetheless, it is clear that Weizenbaum’s secretary actually used the ELIZA system. As he writes in Weizenbaum (1967: 477):

My secretary watched me work on this program over a long period of time. One day she asked to be permitted to talk with the system. Of course, she knew she was talking to a machine. Yet, after I watched her type in a few sentences she turned to me and said “Would you mind leaving the room, please?”

Weizenbaum writes about the effect, later actually coined the “Eliza Effect”, that this dyadic conversation could have between user and computer:

What I had not realized is that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people. This insight led me to attach new importance to questions of the relationship between the individual and the computer, and hence to resolve to think about them.

The Eliza Effect is the propensity for humans to ascribe understanding and intelligence to computer systems. Hofstadter (1995: 167) described it as “the susceptibility of people to read far more understanding than is warranted into strings of symbols — especially words — strung together by computers”, a compelling description written in 1995 but which accurately describes generative AI systems today like ChatGPT. Similarly, Turkle described that “the Eliza effect refers to our more general tendency to treat responsive computer programs as more intelligent than they really are. Very small amounts of interactivity cause us to project our own complexity onto the undeserving object”.

Chatbot technology has changed tremendously since the 1960s. Human nature has not changed at all.

App Icon Conventions From the Original Macintosh ★

Dr. Drang, in a post replete with examples of icons of popular apps from the original Macintosh, in their one-bit glory:

You can see that Apple liked the idea of app icons being a tilted rectangle with some image inside the rectangle to indicate what the app did. The hand was Apple’s way of telling you that this icon was for doing things, and the rectangle was tilted to match the orientation of the hand. (If you were left-handed, this was just another injustice inflicted on you by a cruel right-handed world.)

Document icons were typically upright rectangles with dog-eared corners and similar designs inside the rectangle — no hands because documents don’t do anything. But we’re not here to talk about document icons.

I never loved the hand on these icons. It felt too uniform. It functioned like a “this is an application” badge, but such a badge never felt necessary to me. But it was so ubiquitous I sort of stopped seeing it, and now, in hindsight, it holds some nostalgic warmth. Right from the start, though, TeachText didn’t have a hand — just a pencil:

[Update: Turns out TeachText didn’t appear until 1986 and System 4.1. Before that, MacWrite was bundled with the Macintosh and served as the system text document reader. I wrongly thought that TeachText was part of System 1 because it’s on Infinite Mac’s System 1 disk image; but that image contains apps from the future that still ran with backwards compatibility on System 1. You can see the 1986 copyright in TeachText’s about box, which also gives credit by name to its author at Apple, Bryan Stearns. It may well be the case that all app icons from Apple for System 1 in 1984 had the hand-with-tool badge.]

That TeachText icon was prescient about the future of good icon design. A year later the renamed and expanded (it now moved desk accessories in addition to fonts) Font/DA Mover lost the hand and became a fun truck (also prescient of great icons to come):

(So many little things were still in flux in those primordial days. Note the bold text in the Finder window status bar header in System 1. That kind of looks cool, though. But the single-story “a” in the Geneva font — that’s just wrong, and gives me the ick.)

Drang continues:

Other publishers abandoned either the hands or the tilted rectangle or both. As people got more used to working with Macs, these clues for what’s an app and what isn’t became unnecessary, and icon design became less constrained. Even Apple gave up on them for utilities like Disk First Aid and Font/DA Mover.

I think it’s less that Apple gave up on them and more that it came into focus that the “hand holding a pen over a diamond-shaped document” convention was intended for document-based apps. It signified “This is a creative tool that you use to create documents”. Apps that weren’t about creating document files — like Disk First Aid and Font/DA Mover — got different icons. Font/DA Mover’s truck icon in System 2 signified that you use this tool to move things. Disk First Aid’s ambulance was an obvious metaphor for repairing something unwell. Moving and repairing are very different purposes from creating. Font Mover’s icon in System 1 wrongly suggested, if only subtly, that it was a tool for creating font-related document files of some sort.

But the main thing about the “hand holding pen over diamond” convention was that it was only ever a convention. If Apple’s squircle fetish were merely a convention, then third-party developers would be free to ignore it. Some conventions are merely fads — they come into and out of vogue quickly. Some are long-term trends that persist. But the ones that prove to be more than passing fads win out on merit in the marketplace of ideas. Mandating the squircles with squircle jail doesn’t make them a winning idea. It’s like claiming to win elections when credible rivals aren’t permitted on the ballots.

(Also, I am in complete agreement with Drang re: my favorite app icon of that era. So perfect, so fun, but so ineffable as to why it’s so perfect.)