All chat bots suffer this flaw.

GUIs solve it.

CLIs could be said to have it, but there is no invitation to guess, and no one pretends you don’t need the manual.

And furthermore - aren't there shells that will give you the --help if you try to tab-complete certain commands? Obviously there's the issue of a lack of standardization for how command-line switches work, but broadly speaking it's not difficult to have a list of common (or even uncommon) commands and how their args work.

(spends a few minutes researching...)

This project evidently exists, and I think it's even fairly well supported in e.g. Debian-based systems: https://github.com/scop/bash-completion.

"Hunt the verb" means that the user doesn't know which commands (verbs) exist. Which a neophyte at a blank console will not. This absolutely is a problem with CLIs.

Many users like myself enjoy a good manual and will lean into a CLI at every opportunity. This is absolutely counter to the value proposition of a natural language assistant.

But the point is none of that is intrinsic or interesting to the underlying idea, it’s just of annoying practical relevance to interfacing with APIs today

Every time I try to interact with one of these llm gatekeepers I just say what I want and hope it figures out to send me to a person. The rest of the time I’m trying to convince the Taco Bell to record a customer complaint about how its existence itself is dystopian.

> but there is no invitation to guess, and no one pretends you don’t need the manual

which is basically what you're saying too? the problem with voice UIs and some LLM tools is that it's unclear which options and tools exist and there's no documentation of it.

If you ask Siri about playing some music, it will go the dumb route of finding the tracks that seems to be a close linguistic match of what you said (if it correctly understood you in the first place) when in fact you may have meant another track of the same name. Which means you always need to overspecify with lots of details (like the artist and album) and that defeat the purpose of having an "assistant".

Another example would be asking it to call your father, which it will fail to do so unless you have correctly filled the contact card with a relation field linked to you. So you need to fill in all the details about everyone (and remember what name/details you used), otherwise you are stuck just relying on rigid naming like a phone book. Moderately useful and since it require upfront work the payoff potential isn't very good. If Siri would be able to figure out who's who just from the communications happening on your device, it could be better, but Apple has dug itself into a hole with their privacy marketing.

The whole point of an (human) assistant is that it knows you, your behaviors, how you think, what you like. So he/she can help you with less effort on your part because you don't have to overspecify every details that would be obvious to you and anyone who knows you well enough. Siri is hopeless because it doesn't really know you, it only use some very simple heuristic to try to be useful. One example is how it always offer to give me the route home when I turn on the car, even when I'm only running errands and the next stop is just another shop. It is not only unhelpful but annoying because giving me the route home when I'm only a few kilometers away is not particularly useful in the first place.

For older tools, sure. Newer tools eschew man pages and just offer some help flag, even though there are excellent libraries that generate manpages like https://crates.io/crates/clap_mangen or https://crates.io/crates/mandown (for Rust, but I am sure most languages have one) without requiring you to learn troff.

An AI wrapper typically has few actual capabilities, concealed behind a skeuomorphic “fake person” UX. It may have a private list of capabilities but it otherwise doesn’t know if it knows something or not and will just say stuff.

It really needs to be 100% before it’s useful and not just frustrating.

- almost every search field (when an end user modifies the search instead of clicking one of the results for the second time that should be a clear signal that something is off.)

- almost every chat bot (Don't even get me started about the Fisher Price toy level of interactions provided by most of them. And worse: I know they can be great, one company I interact with now has a great one and a previous company I worked for had another great one. It just seems people throw chatbots at the page like it is a checkbox that needs to be checked.)

- almost all server logs (what pages are people linking to that now return 404?)

- referer headers (you product is being discussed in an open forum and no one cares to even read it?)

We collect so much data and then we don't use it for anything that could actually delight our users. Either it is thrown away or worse it is fed back into "targeted" advertising that besides being an ugly idea also seems to be a stupid idea in many cases: years go by betweeen each time I see a "targeted" ad that actually makes me want to buy something, much less actually buy something.

Very charitable, but rarely true.

I’m looking at you, Photos sync.

EDIT: just noticed this exact problem is on the front page in its own right (https://eclecticlight.co/2025/11/30/last-week-on-my-mac-losi...)

Will it sync? When? Who knows? You’re on WiFi with a full battery and charging? So? Might be a minute, might be an hour. Oh, you restarted Photos? Who cares? Not Photos.

I literally just experienced this with RCS failing to activate. No failure message, dug into logs, says userinteractionrequired. Front page of HN, nobody knows, apple corp response, 'thats interesting no you cant talk to engineering'.

Read the RCS spec definition document to fall asleep to after the board swap and the call saying they won't work on it since issue resolved, answers exactly what that meant, Apple never implemented handling for it, my followup post: https://wt.gd/working-rcs-messaging

Knowing that a company had competent product designers that made a good product, but then shitcanned the working product for a bunch of amateur output from people that don't understand dry very basics of UI, from the one company that made good UI its primary feature for decades... well it just felt like full on betrayal. The same thing happened with absolutely shitty Apple Music, which I never, ever use, because it's so painful to remember what could have been with iTunes...

I don't know why it bugs me so much, but I'm at the point of moving my library into a self-hosted Navidrome instance so I can stop using Music.

I remember advising many photographs friends on using Aperture for photo library management. Now I feel so bad for ever recommending that. I mean Lightroom now has a stupid subscription, but using Apple software was kind of the point: avoiding the risk of software becoming too expensive or bad because the hardware premium funds the development of good software.

Now you get to pay more for the hardware but you have to deal with shitty or expensive software as well. Makes no sense.

The list didn’t show the god damn GoPro app, which was taking up 20GB of space from downloaded videos. I guessed it was the problem because it showed up in the device storage list, but literally not reported when you look at the list of data to backup.

iMessage is another great example of a failure. I changed my iMessage email and didn’t receive messages in a family group chat until I noticed — I had to text the chat before stuff started coning through. Previously sent messages were never delivered. And they all have my phone number, which has been my primary iMessage for LITERALLY over a decade. iMessage’s identity system is seriously messed up on a fundamental level. (I’ve had numerous other issues with it, but I’ll digress.)

I've found I appreciate having Siri for a few things, but it's not good enough to make it something I reach for frequently. Once burned, twice shy.

This is why LLMs are the first conversational interface to actually have a chance of working, once you give them enough tools.

are there solutions to the error rates when picking from dozens or even hundreds of tools i'm not aware of?

[1] Made up title