'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

@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?

@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.

Follow

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

Sign in to participate in the conversation
hackers.town

A bunch of technomancers in the fediverse. Keep it fairly clean please. This arcology is for all who wash up upon it's digital shore.