'User agent' is a great idea that has been weirdly perverted.

Nobody these days (even highly technical people) has a user agent. (Maybe @drwho does.)

A user agent is a piece of software controlled by the *user*, that performs the automatic tasks the *user* has instructed it to. It communicates with other user agents, automatically, on the user's behalf.

Today, the term 'user agent' means 'long, misleading browser-lineage-identification string'. It identifies one of ~3 corporations.

Imagine if we actually *had* user agents.

Like, imagine if our computers were doing things we wanted them to do, automatically, on the network. And, it was our computers doing these things, instead of a rental service like ifttt or google alerts that's selling info on the back end. Imagine if they stopped doing things when we told them to stop.

Imagine if non-technical users had this too.

'User agent' is basically 'daemon, but controlled by an end user'. And, it's a thing we really need & don't have.

@enkiv2 I remember I think it was the early 1990s, lots of talk about 'software agents'. They were sort of the buzzword term, the 'neural networks' of that decade.

I don't really understand even now what lab that hype came from, and why it went away?

@natecull @enkiv2 i've never really found the "software agents" line of thinking very compelling, or at least it hasn't been very compellingly _presented_. it always felt like hype in much the way that VR or that weird brief period when XML was going to save the world did.

on the other hand, if the idea is just that people should own and control computers which do things with their data in their interests, well, that sure does sound like a pleasant contrast to the status quo.

@brennen I can say that even the term "software agent" sounds sort of dull, uninterestingly hands-off, and like something the average person wouldn't think they needed or was qualified to mess with.

Exactly the opposite of the hands-on, approachable, and self-ownership feel that future tech stuff needs to have.

Meaning no offense.
@natecull @enkiv2

Follow

@erosdiscordia @brennen @enkiv2

Well, on the one hand, part of the 'software agent' fuss was sort of linked with, um, personal organizers, early handhelds, the idea of an 'electronic butler/secretary' and so there WAS quite a bit of that 'hands-on, approachable' hype about it? You'd have a personal 'Agent' who would be a sort of pseudo-personality in your computer?

But then the other side of the 'software agents' thing was... mobile code, that you'd transmit? I guess 'cloud server' ate that?

@erosdiscordia @brennen @enkiv2

and then the success of the 'search enginet' model, and Google with it, sort of led to the idea of the 'agent' being a personalised service provided by Extremely Large Corporations rather than an actual thing you'd own and control

so the 'agent' got replaced by the idea of 'portal', then 'portal' as a buzzword got replaced by 'app' after the iPhone got big and mobile became the interface to the same Extremely Large Corporation pretending to be your tiny friend

@erosdiscordia @brennen @enkiv2

so now we get companies like Trivago advertising comparison services on TV, and the company-service-slash-app-slash-website-slash-portal-slash-agent they provide is essentially the same idea as those 1990s 'shopping agent' concepts? At least that's what they claim. But how do you know they're not messing you around? they almost certainly are or how would they make money?

@natecull Back in the 90s those "shopping agents" (websites, proto-apps) wanted to take money out of your hand. Now they want to sell you to someone else, while still gaslighting you that you're the lord of all creation. It fuckin sucks.
@brennen @enkiv2

@natecull You're nailing it here.

I think people need to take a look at how much sunshine they let be blown up their butts too, though. Being sold "experiences" and "services" (that turned out to be data-mining ventures) was presented as more aspirational than owning or doing anything for yourself, and people went with it.

@brennen @enkiv2

@natecull @erosdiscordia @brennen @enkiv2 More or less. Wifi didn't catch on fast enough and cellular data was hella expensive in the US until just recently.

@natecull @erosdiscordia @brennen @enkiv2 How people think of something complex (like software agents) is to a large extent controlled by how they /can/ think of them. The cultural referent has to be there first, the framework for understanding what a thing is and what a thing can be.

@drwho Hmmm. Maybe they could be presented as assistants/agents, or also as a type of power that a user has.
@natecull @brennen @enkiv2

@erosdiscordia @drwho @natecull @brennen

I think the most important thing about them is that they keep on doing things on the user's behalf when the user isn't there. This is something that end users aren't used to: that they can *control* an automated process.

@enkiv2 @drwho @natecull @brennen This point of yours nails something, I think.

Average users have been sold a sort of all-or-nothing mentality -- either be a super-hacker, or sit back and accept whatever you're shown, by the app or the site or your OS, etc.

There are already other options, and I think people are increasingly hungry for them.

@erosdiscordia @enkiv2 @natecull @brennen They do seem to be hungry for other options, but they need t be introduced in a way that doesn't make them immediately think they're too hard.

@drwho @erosdiscordia @natecull @brennen

I think something that's seriously underused in this context is planners.

Like, no voice assistant understands "I want to do <x> in such a way that <y> but not <z>" but that's something we've known how to implement since the 70s.

A conversational interface to a planner (in order to identify ambiguous situations & clarify them) that then controls what amounts to shell scripts -- that's UI heaven.

@enkiv2 @erosdiscordia @natecull @brennen Amy at x.ai does that pretty well. Some Slack bots also do that pretty well in the devops world, we use them at $dayjob pretty heavily.

Indeed! Writing one is on my to-do list, but I need to get Kodibot functional first.

@drwho @enkiv2 @erosdiscordia @brennen

I am enjoying playing with Node.js more and more and I wonder if that can be the foundation for agent-like tools.

Mostly because it's mainstream enough to get lots of support, can run as a server, and it's reflective/lightweight/dynamic enough to be able to implement all sorts of AI techniques, up to and including brute-force reimplementation of Lisp.

@natecull @enkiv2 @erosdiscordia @brennen It's used to write a lot of Slack bots for those very reasons.

@drwho @enkiv2 @erosdiscordia @brennen

Frankly I think we need something a lot simpler than Javascript to be secure, but, Node at least is a reasonable prototyping environment

compared to say, Racket, which I just can't get into, and Python, which I can't get past the whitespace stuff (plays major havoc with my copy/paste to the REPL style)

@natecull @enkiv2 @erosdiscordia @brennen FWIW I love using Python for bots.

I think that we need fewer languages to do so, and more frameworks. IFTTT took off because it makes this sort of thing really easy. Huginn works about as well but it's more hands-on about stuff.

@drwho @enkiv2 @erosdiscordia @natecull @brennen "Amy at x.ai" does that by being largely backed by actual humans, going by bloomberg.com/news/articles/20 . We're not there yet, but that doesn't mean people don't want to pretend otherwise.

@drwho Very true. I've been a victim of feeling intimidated by the tech world for a long time, so I can relate to this. Nothing sucks worse for the average user than some smart person going, "It's easy! You just have to (unintelligible) the (incomprehensible)! An idiot could do it!"
@enkiv2 @natecull @brennen

@erosdiscordia @drwho @enkiv2 @brennen

"and OBVOUSLY don't touch the blue and red wires, I mean every fool knows THAT, it'll explode and burn down your house"

"uh, ok, so, could you make a version without the red wires then"

"hell no! better let lots of houses burn down! it keeps the idiots out! heh heh heh!"

@natecull
Exactly! And not to get too on the nose, but it's linked to the lack of diversity in tech, and the awful rates of accessibility for a lot of people who even ARE interested in helping out and contributing. There are very strict on-ramps to this exploration right now, and that sucks. It's a big part of what open-source and automation should address.
@drwho @enkiv2 @brennen

@erosdiscordia @natecull @enkiv2 @brennen Indeed. They say they want different points of view, but when they get them, they promptly ignore them. A lot of F/OSS projects are the same way. A lot of F/OSS projects that deliberately seek diversity (and I'll toot my own vuvuzula here) are having a hell of a time getting any help.

Also, UI/UX is really hard.

@drwho There is so much to learn, in the free moments I have between trying to get a survival job. Sometimes I have to take deep breaths and try not to get pissed about how deliberately I got steered away from tech stuff and slapped down for my interest in it. It just makes me more determined to figure out my place in it, though.

I'm really glad I stumbled across a site where people talk about tech in a truly friendly way. Thanks.
@natecull @enkiv2 @brennen

@enkiv2 @erosdiscordia @natecull @brennen Very true. Most users get really frustrated at automated processes because they tend to get in the way at the worst times, like antivirus scans in the middle of a game. That's a power dynamic issue.

@drwho @enkiv2 @erosdiscordia @brennen

It is amazing the fuss I have sometimes just *changing the volume of the speaker*, with multiple apps conflicting, the OS being slow to respond, to the point that having a *physical plug in a physical socket* is more reliable.

until we can fix stuff like this, we don't have much chance in heck getting much more complex agents than 'audio volume' to communicate in ways that give the user satisfaction.

@drwho To be honest, as much as I don't love Alexa/Cortana/Siri, they've all done a good job of moving people past the trauma of Clippy...
@enkiv2 @natecull @brennen

@erosdiscordia @natecull @brennen @enkiv2 A type of power a user has works well for a pitch. Amy at x.ai capitalized on that version of the meme to good effect.

@drwho I'm actually revisiting this (very good) point in light of current science fiction trends, and the need I see for SFF to explore something besides dystopia / authoritarian /hierarchical grimdark narratives. I think that shift has already begun, and I wonder how it might link up to some of these tech angles.
@natecull @brennen @enkiv2

@erosdiscordia @natecull @brennen @enkiv2 Check out Eclipse Phase. It's doing a lot to portray "awesome posthuman life as viable alternative to authoritarian screwheads" with a hefty dose of "you can make this happen" mixed in.

The fiction anthology is pretty Firewall-centric, though.

@enkiv2 @drwho @erosdiscordia @brennen

Wasn't there also a 1990s/2000s tabletop transhumanist RPG called Eclipse Phase?

@natecull @erosdiscordia @brennen @enkiv2 part of the issue is that "software agents" was used in the late 90s to mean a lot of different peripherally related things… mobile code, filtering rules, ifttt-type triggers, and I think even at one point program trading (of securities)

@kragen @natecull @erosdiscordia @brennen

I think they really are all user agents, because user agent is a term not specific to function.

Anything that is automated but also controlled by a non-technical end user is a user agent.

So the promise is that you can *use* a team of interacting user agents, and each one of them would do a different specific thing, in response perhaps to a user agent whose job was coordinating plans with the user.

@kragen @erosdiscordia @brennen @enkiv2

oh, definitely!

That's part of the weirdness around the term. It got generalised to the point where it meant 'any program doing anything' and at that point.... why even use it?

@natecull @kragen @erosdiscordia @brennen

Something that got lost in translation is that user agents should be communicating with each other. I think if we had a "user agent communication standard", even if we just renamed jabber, it would be less of an issue.

Download a new user agent from 'inhuman resources' or 'central casting' to do a particular job & it checks in with your assistant agent to plug into your planner system, whatever.

@enkiv2 @kragen @erosdiscordia @brennen

aaand InhumanResources will be hacked with garbage agents just like app stores and npm repositories in 3, 2...

The problem with Extremely Large Corporations is that people think having an ELC's name on it makes a product/service secure.

@enkiv2 @natecull @erosdiscordia @brennen This is wrong, historically speaking. AFAIK the origin of the term "user agent" is in email; it's in e.g. tools.ietf.org/html/rfc1341 from 1992. Also in POP3 tools.ietf.org/html/rfc1081 from 1988. In hat context there was definitely not the idea that one user would usually have several agents or that the agents would talk to each other directly. In 1982 RFC 822 doesn't say "user agent" and uses "agent" in an incompatible way.

@kragen @natecull @erosdiscordia @brennen
That chronology can't be right. The term 'user agent' was used in science fiction in this way in the mid 80s, at the latest.

I'll take a look, but I've got a sneaking suspicion that the idea of a user agent is about as old as the idea of the filter bubble (the 'Daily Me' proposed at Negroponte's lab in the late 70s) or the Internet of Things ('Ubiquitous Computing' at PARC around 1979).

@enkiv2 @kragen @erosdiscordia @brennen

'Agent' has been a term of art in mail handling for a while, hasn't it? 'Mail User Agent' 'Message Transfer Agent' . Makes sense that HTTP inherited SMTP terminology.

But where did that 'agent' terminology come from, I wonder? And when? Mid-1980s, I assume?

@natecull @enkiv2 @erosdiscordia @brennen Well, those RFCs suggest that it wasn't current in the Internet mail world in 1982, and in 1988 required explanation, so sometime between 1982 and 1988. I suspect they might be loanwords from OSI X.400.

@enkiv2 @kragen @erosdiscordia @brennen

As kragen said, RFC 822 (1982) uses the term agent:

'AGENT (person, system or process)'

which makes sense that it was an abstracted concept for 'person or system' in, I guess, DARPA systems thinking around then?

@natecull @enkiv2 @erosdiscordia @brennen Read it more carefully, though; it's talking about secretaries or people loaning you their terminals, not Rmail.

@kragen @enkiv2 @erosdiscordia @brennen

Person *or* program.

<< The Sender mailbox specification includes a word sequence which must correspond to a specific agent (i.e., a human user or a computer program) rather than a standard address. ... For example in the case of a shared login name, the name, by itself, would not be adequate. >>

@natecull @kragen @erosdiscordia @brennen

Wikipedia is claiming that the concept of the software agent has its origin in the actor model (so, early 1970s). This makes sense: 'agent' and 'actor' share etymology, & 'agent' is a less misleading way to express 'one who performs actions' -- particularly 'one who acts on behalf of another'.

Actor model has, inside it, the assumption that agents communicate with other agents.

@enkiv2 @natecull @erosdiscordia @brennen That's probably a rogue edit by Carl before he got banned from Wikipedia for claiming everything cames from acors

Sign in to participate in the conversation
Mastodon

Server run by the main developers of the project 🐘 It is not focused on any particular niche interest - everyone is welcome as long as you follow our code of conduct!