Man, just when it seemed like we had it all. Computers were cheap, efficient and powerful. Somehow we figured out a way to accomplish tasks we already had solved except now it's 1000x more expensive, requires the combined electricity of the entire world, is reliant on someone else's rented compute, and now I need a robot to tell me what button to press. What a time to be alive.
In 40 year software designers couldn't figure out that there should be a search function for every functionality that your computer provides.
When we got a form of such search, it searched all of the internet alongside with the functions of your software on your computer. You had to tell it manually what software you have and when it found something you had to fish out the description of what to click to get the functionality you are seeking and then click through some dumb ui to actually invoke it.
Agents are the first thing that can lead you directly from "I know what I want my computer to do." to "Actually doing it."
Success of agents is founded on the profound and sustained failure of all of the software designers and developers ever.
$ apropos dns
[...]
resolvectl (1) - Resolve domain names, IPV4 and IPv6 addresses, DNS resource records, and services; introspect and reconfigure the DNS resolver
[...]
$ man resolvectl
[...]
dns [LINK [SERVER...]], domain [LINK [DOMAIN...]], default-route [LINK [BOOL...]], llmnr [LINK [MODE]], mdns [LINK [MODE]], dnssec [LINK [MODE]], dnsovertls [LINK [MODE]], nta [LINK [DOMAIN...]]
Get/set per-interface DNS configuration. These commands may be used
to configure various DNS settings for network interfaces. These
commands may be used to inform systemd-resolved or systemd-networkd
about per-interface DNS configuration determined through external
means. The dns command expects IPv4 or IPv6 address specifications
of DNS servers to use. Each address can optionally take a port
number separated with ":", a network interface name or index
separated with "%", and a Server Name Indication (SNI) separated
with "#". When IPv6 address is specified with a port number, then
the address must be in the square brackets. That is, the acceptable
full formats are "111.222.333.444:9953%ifname#example.com" for IPv4
and "[1111:2222::3333]:9953%ifname#example.com" for IPv6. The
domain command expects valid DNS domains, possibly prefixed with
"~", and configures a per-interface search or route-only domain.
The default-route command expects a boolean parameter, and
configures whether the link may be used as default route for DNS
lookups, i.e. if it is suitable for lookups on domains no other
link explicitly is configured for. The llmnr, mdns, dnssec and
dnsovertls commands may be used to configure the per-interface
LLMNR, MulticastDNS, DNSSEC and DNSOverTLS settings. Finally, nta
command may be used to configure additional per-interface DNSSEC
NTA domains.
Commands dns, domain and nta can take a single empty string
argument to clear their respective value lists.
For details about these settings, their possible values and their
effect, see the corresponding settings in systemd.network(5).
[...]
Not too bad in my opinion. (I didn't actually knew before how to set the DNS server, never needed to do it.)
Quite uselsess, it doesn't tell me which file to edit, what to put in there, nor what command to invoke with what arguments.
People can do and do better with googling. Proportion of people who found the answer to that question through apropos to people who found that answer googling is probably less than a million to one.
The man pages certainly tell you how to set your DNS to 8.8.8.8. You just have to do a bit more reading than what the agent would give you. But there's a side benefit to that extra reading, you learn how to do more things. Sometimes that's useful, sometimes it isn't. But you don't know if it is useful or not until later, you can only find out in time
I’m not sure I understand the desire to control computers with conversational language. Computers are a collection of on off switches. I personally would much prefer being able to control exactly which on off switches to switch, instead of just telling the black box to do something and for it to make no mistakes. It just doesn’t strike me as a good idea to give the incomprehensible matrix weight the ability to make decisions about what to do on my machine. There’s just far too much ambiguity for my comfort here.
I sort of agree that this is the consequence of software hell but it's not so much designers couldn't figure out the need for search from the start but that designers gradually made things so complicated you needed a global search functionality and then didn't provide it.
I mean, Android settings has global search because the settings menus for each Android phone is different (wtf) and some settings aren't even accessible except searching.
"He" isn't even covering it, he eventually automated himself out of the channel: He AI-cloned his voice and had it read AI-generated scripts. I assume he still does.
i've read enough 'shlemiel the painter' ports across hundreds of systems and thousands of examples that I must quickly and coldly dismiss the precept that computers were ever used efficiently.
I am willing to bet you could run a model capable of using this on a 12GB 3060 + some RAM. (Qwen 3.6 35B)
Even the data centre using this probably uses less net energy, and costs less, to build one of these dumb arrows than the aggregate sum of the energy used to keep you alive while you Googled for the answer. (Including heating/cooling the building, powering the equipment growing the food you eat, etc.)
I don't disagree. But the existing tech solution - scrubbing through YouTube tutorial videos until I cobble together the bits of knowledge I need - is also quite overengineered, isn't it?
Obviously I'd prefer to ask specific questions to my expert human friend sitting at the next desk over, but sadly they don't exist.
I just hope there is a future where this tech exists without such big downsides.
There'll be gauntlets of pathways mapped before the first step is taken, as or before the first agent is deployed. Criteria will include resource use weighted against economic efficiency. Already being done.
Sounds like an opportunity for a good engineer to come in and write something with the same functionality that runs locally and efficiently. The claim that it's wasteful only holds water if the non-wasteful solution exists and can accomplish the same tasks.
>Imagine if videogames needed an external datacenter to run the tutorial levels.
I don't see how this is anything like that. The point here is to make it easier to give the user indications which has been a staple since forever, hell this is so much of a problem that there are entire solutions engineered to letting one user take control of the computer of another user through the net.
Beyond that, I'm sorry but looking for help in the context of videogames is extremely prevalent. That external datacenter to run the tutorial levels is sometimes called "Youtube" and others "Wikia".
For ages people have been saying "it's obvious" or "it's intuitive", without learning anything about design principles. Obvious to who?
People have been saying "we don't need docs", "nobody reads docs", "they'll figure it out". They experience the pain of a new employee onboarding but never treat this as a signal for the user experience. The user can't just walk over to the developer's desk. But luckily we got stack overflow, blogs, and Google. Somewhere someone explains it! The problem became finding it!
But hey, why do things the "hard" way when you can just throw money at the problem? Or better yet, dismiss the problem by calling the user an idiot.
You're right. What a time to be alive. We've created a world where this product is useful. And not even to because dark patterns exist, but simply because we've always wanted to avoid taking a step back and thinking or getting an outside view. Because it isn't obvious if a robot has to teach you what button to press. If it does, you probably should be ashamed (there are, as always, exceptions)
That said, I do think there's still a lot of utility you this. Those exceptions aren't uncommon. This'll help people learn programs like FreeCAD or Blender, or whatever. Where the complexity is naturally high. But also I do think we should recognize the silliness of many problems that this does solve that shouldn't be problems in the first place.
Garage sale signs are a good example of this. The person making the sign knows what it says, so they can "read" it from farther away than someone who doesn't already know what it says.
It was still the human writing the code. In the last several years it's become the human writing the prompt, which has led to agentic development, and the next step seems to be removing the human from managing the agents.
I'm sorry but I am just so tired of hearing this lazy logic. A C compiler is largely a 1:1, deterministic pattern matcher. I type X, I can be reasonably sure compiler will do Y.
An agent is not at all like this. The freaks who made this disingenuous machine don't even know how or why it does half the stuff it does. We're all just throwing shit at the wall and seeing what sticks. Absolute nonsense take my man, I'm sorry.
There is a huge difference between mathematical determinism and "it looks like that thing I said." Even the laziest, most superficial analysis must conclude these two things are not the same just because they have vaguely the same shaped shadow.
There's also a huge difference between formalizing your problem in a set of strict rules that take a lifetime to master and saying "make me a todo app, make no mistakes".
On the other hand, (while you made a completely valid point,) some people who are new to a field, like young aspiring computer scientists who don't know how to do some stuff and need a guiding hand, will find this tremendously useful. Also, technology and compute power has been growing a tremendous amount over the past 5-10 years (now we have 20-100 billion transistors in chips!). <-- enough to sustain this wild use of compute
I’m really curious about the end game. When this technology completely saturates and AI becomes his mundane bullshit thing know one cares about but uses all the time. Like the next level above slop. I wonder what that world will look like.
I also am curious of this, I only fear that it's going to turn into a concerted effort by those who have power to remove already existing capabilities from individuals and replace it with centralized infrastructure. Swapping out everyone's desktop for a think client hooked up to an agent and renting it back for a monthly fee for example, would be a strict downgrade when we already had the capability to do pretty much anything we could think of on the internet. Sure maybe it makes someone's workflow a b it more efficient, but I quite like having my own agency. I don't intend to hand it away some dork who owns a billion GPUs can rent it back to me.
If you look at the example animations, it's clear that Apple has brought this entirely upon themselves. Don't yell at some guys who are trying to fix it.
I agree, actually. And I’m more than happy to criticize anyone and everyone involved as the state of software is in my opinion a failure of the human race. So I’ll yell at whomever I want, thanks. They’ll be ok.
