My budget app, for example: It’s not easier for me to ask the AI bot “show me all my transactions from McDonald’s” than it is to click on the search bar/payee filter and type “McDonald’s.”
But if I use the AI bot, I’m burning tokens.
The UX experience for basically all LLMs that I've interacted with is having the AI sneak in where I don't want it and end up taking 10 extra seconds to do what used to be a 0.1ms operation.
The worst place for AI is in search bars, yet that seems to be the first place every product manager wants to put it. I hate waiting forever to get results because AI is poorly searching in the foreground.
... One wonders if that is due to the great implementation of the bot, or due to the less than stellar results of confluence search.
It does automatically write the PR in the first place but if you delete that description then try to have Rovo make a new one it fails hard.
[0] as of a couple of months ago when I last tried reformatting a slide deck using Gemini (failed) and then Claude (succeeded)
Rovo makes changes I don't want that I have to undo and its "search" is bafflingly low quality compared to the old search experience, but most of all it just makes every page take longer to load and puts annoying UI elements in the way of what I actually want to interact with.
It mirrors every single other in-app AI bot experience I've had to date - less useful than the functionality they replaced with it, slow and annoying.
The only one I’ve enjoyed is Grafana’s. It’s been a joy to use tbh.
The “copilot” instances built into Microsoft’s programs are almost entirely useless due to this.
Those tradeoffs must be considered when deciding whether a feature requires regular software or AI.
A few repeats of the same initial light adjustment and she had a big joker grin and the CEO had giant anime eyes and looked 25 years younger.
Now, if we were to do this first "fix the light" pass on every publicity photo, what would it be adding and taking away without our knowledge? I fundamentally don't like using a tool that will do other things than what I want it to do, without even warning me. The consequences of a noticeable fuckup will be on me, not on the machine, so I'd rather adjust the slider myself thank you.
I think a good chunk of people just do not ever try to understand what buttons do, ever, and it's maddening.
I experienced it this morning asking for Google maps to be set to alerts-only mode: "I'm sorry, I can only turn voice guidance fully on or fully off."
I recently setup Muse (just seems to have the easiest out of the box connectors) to connect to all my accounts over Plaid. I can ask questions like: * Review all recurring transactions. * Show overview of last 12 months of spending by category. * Review last months CC transactions. * Estimate next months expenses.
And then in the same app, I automatically get personal financial and budget information that's actual useful. I can adjust the frequency and type of content just by updating the agent's goal.
I tried using YNAB. It felt so cumbersome compared to just asking AI for the info. I had to make a $300 fake expense to zero out an account minimium balance, I can't treat an investment account as a spending account (without some weird hacks).
Meanwhile, the same AI can cleanup my email inbox, watch my calendar, etc.
And I spent like ~2 days having Claude (over remote-control) create a Monte-Carlo simulation for retirement (including Tax calculations). Works great, I can read the code and make whatever changes I need.
The most friction I still encounter is the connector itself being too opinionated. Plaid's API tries to predict future expenses based on what's detected as a recurring charge; this of course was incorrect if similar Amazon.com charge amounts occur on similar days.
IMO purpose built apps are dead. A sandbox of tools that AI can use is far more flexible. Spending $20/month only needs to replace 3-4 other paid single purpose apps (or identify a single $20 recurring service to cancel) to be net-positive. Plus you don't have to configure it, just ask questions.
This is the biggest indicator of the divide between the AI-enthusiastic developer and the average person.
The average person isn’t going to want to sit down and spend two days to fine-tune code or a spreadsheet to accomplish this. They want an easy-to-navigate interface that is dead-simple and ready to go with the ability to get an answer done in five minutes or less. If they hit any snags in the first 30 seconds they’ll ditch it and move to the next solution. Why should they have to spend their time creating a duplicate solution when there are so many ready-to-go alternatives already out there? They want the path of least resistance.
I think for people who can quickly understand and describe systems/code, AI is very magical. So many personal projects would be otherwise too tiring except for the 0.1% OSS developer personality that can spend 4+ hours a day working on stuff. Now AI means many projects can be implemented at the speed of thought.
i can understand it with the “i’m gonna optimize everything to death crowd” probably eat the same thing every week. i couldn’t do it though, i get bored with the same food. its also why i can’t wear the same sweater every day lol.
Even apps can be strictly worse than lower tech solutions.
A local car service I can text with “I need a car to airport XYZ tomorrow at 7am” beats every app flow.
i programming stuff using LLM of which the resultant programs are deterministic and dont use LLMs or tokens is a better or easier approach to having gains. because the resulting program can be easier to use and doesnt cost a lot to run. Automations are a good target, or integratig libraries into other programs. tedious things u know well how to do but take time to do manually. then once done fix a problem or workflow that u need fixed by the solution yielded.
ive not seen 1 app that does calls to an LLM that i find useful, apart from harnesses that produce code (which is only recently becoming more appealing and might depend on how good and fast u can write code, at which im not the best nor the fastest.)
Tailoring + proofing resumes to _manually_ apply to jobs is a great application of LLMs in my experience. But I wouldn’t want an AI to apply for jobs for me.
Recruiters said it was standing out in the tech sector. Apparently AI likes to embellish way too much so you don’t trust it.
why? they’re using ai for most of the hiring process. it’s only fair for us to do it too.
I think we’re on path to just do random full review audits of maybe 10% to get a baseline confidence level and then just note it as a risk. Still a large manual task, we’ll probably outsource it.
I'd ask why and they'd just shrug, like *obviously* google is the front page for everything on the web.
Your anecdote is spot on and it feels like the people who are doing things that way are channeling similar energy.
And these type of requests consume very little tokens in comparison to almost any programming work.
Depending on the level of trust or importance of the decision this may already be a fairly high bar to clear before being able to claim any overall reductions in the interactions itself.
It's worth considering whether you really want the full list of MCD transactions or is that just a step you're used to as a means to getting the answer you want.
Why can I not just type the new name into the title field itself? Well, this is supposedly easier and in time the AI will learn and get the title right 100% of the time, so there won't be a need for me to edit it.
This is a major player in the industry, not some random kid.
It's just "I want the computer to figure this out for me even if it takes longer than the old tools, because I cannot be bothered to learn how to use the old tools"
I've encountered this a lot
Someone didn’t like how our Jira tickets and Confluence docs were structured so they vibe-coded a new ticketing system that has a custom web UI with a Microsoft Access database on the back-end. Management and Customers don’t like it for a good range of reasons but he requires everyone who works on his projects to use it.
Another person didn’t like our build script for generating a templated Ansible role so they made some kind of MCP adapter or harness to ask you canned questions on what your role is named and what features to include, then scrapes our docs to get the required directory structure and generates it. It does literally the same thing but sometimes does it wrong and consumes tokens regardless.
It’s like the XKCD comic about competing standards, but accelerated for any person who is minorly inconvenienced and has API tokens to an AI service.
"Sorry, I do not have that information."
So then, "Ok, where do I find it?"
"Sorry, I do not have that information."
What the hell? What is this for? Of course, someone will point out "it's because of regulations" or some technical limitation, sure, I can understand that, but then I must ask the question then why did you think it was worth building?
It's not like the previous tree based bots were good but at least they had a path to speaking with a person.
I suspect nobody ever tried to use the bot.
Most (Note: Not all!) questions you get when you work in a "customer service" role come from lazy, unobservant, or dumb people. So pre-AI, a large business needs an army of people to answer the phone and do things like walking confused people through, step-by-step, how to reset their password. "Did you check your email? Did you check the Spam folder? Did you give it 5-10 minutes?"
So AI is sold with the promise that you can just put it in front of your human agents, and then you'll only need 1/5 the staff (let's set aside the unfortunate economic implications for the other 80%) because most people's questions are stupid and trivial to solve.
Problem is, the dummies can't identify and divert themselves to the bot up front, so the person who loses most (other than the CS agents who lost their jobs) is people like you or me, who only contact customer service when we are reasonably sure there is no way to solve our own problem on the website/the app/by ourselves. We have to argue with a bot which is prompted "You're about to hear from a dummy whose main problem is most likely that he hasn't read any of our ZenDesk support articles, can't operate our website or a computer properly... and he probably has an IQ of 75. Send him answers from the FAQ -- repeatedly if needed -- and try to get him to go away. Don't give up, and don't escalate to an agent unless very specific criteria are met."
I do wish this were real: https://xkcd.com/806/
Actually, maybe it could become real if we benignly "poison" enough online sources so that LLMs actually do it...
Spectrum - we had a voice and a data cable modem (due to location and cabling requirements). Lost the phone service. Called in and the first things I offered them were the MAC addresses off both modems and which one was supposed to be which. That set off the "shit, he knows what he's doing" moment and we got both modems running correctly in less than ten minutes, including IVR and hold time.
Verizon - had a weird ticket that ended up being a NOC issue. Explained the odd backstory of events, a ticket that happened a couple days prior that I was part of a regional outage, and the Tier 1 guy had me hop on a video call to point my camera at my computer at the ONT where I basically did everything without him asking me to (cabling direct, pulling up IP status info, etc, live reboots) and he ran it by a NOC guy remotely and it ended up being a bigger ticket above me. Took an extra day of a regional outage, but that data helped them get rolling.
The next day I get an email at 7pm telling my appointment was successfully rescheduled for 1pm (the same day), none of these match either my og appointment nor the rescheduled one
When I went to the dentist for the appointment the ai assistant supposedly rebooked, they told me there was a mistake and I was assigned a kids dentist.
In the end I had to rebook a third appointment with the receptionist
I switch at the slightest sign of friction.
except it's worse, if you manage to get some info out of it, it could all be just hallucinated, you were told a lie and no one is responsible.
it's like the only purpose is to erect a barrier between the company and its clients.
Of course when you arbitrarily limit the problem domain to some specific example, you can make any tool seem pointless and stupid. It's when you expand your goals to things that aren't trivial that you get benefits.
Do we need not Mathematica or NumPy because calculators can add just fine?
If you're the type who doesn't: probably 90% of the time.
This feels like goal-post moving now, with questions less genuinely curious about an answer and more trying to "get" me. How am I supposed to answer that, it depends on the task and the model and the harness and specific human being using it.
Use it or don't, I don't care, but at least be genuine in the discussion.
There's a huge spec (Level III data) that lets the merchant provide full line item detail with every credit card purchase.
Corporate cards get it, but consumers don't. The payment ecosystem often doesn't even submit it if the card isn't identified as a corporate card.
If you had that, you'd probably need way less "smarts" to build budgeting tools-- no need to try to reconcile bank records with order reciepts.
Here you can phrase it anyway you like and even typo at writing mcdonalds won't stop the machine from giving you the right answer.
i think we fell into a bit of mass cult.
obviously some are easier digital, but it absolutely is not always the case.
concert tickets was the one that hit me the other day. someone had given me physical tickets to a show. i just pulled them out of my pocket, they scanned them and … that was it. i hadn’t done an analog concert ticket since pre-covid times so i kinda forgot how easy it can be. no trying to remember which app i used or which password or searching through email… just pulled them out and that was it. and bonus points i have an actual ticket stub.
Eh, I could see a case where an AI makes ordering for a group easier.