Printing a boarding pass at home works for the flight out. But what about the returning flight?
Just last week I flew back home from SFO. I needed to change the flight at the last minute. The app failed to update with the new flight. The airline had removed all the boarding pass kiosks from that airport and only seemed to have luggage drop service. I asked an airport employee how I could get a boarding pass printed, and he pointed to a poorly-marked lane with a sign about "special accommodations" or something, like I was blind. I waited in that line for about 20 minutes along with people who were trying to check their bags. Eventually I got to someone who seemed really put out that I hadn't checked in yet and that they'd need to push a few more buttons on their computer to do that for me.
Weird, I've flew out of SFO two weeks ago on United, and their online check-in never works for me so I just do it at the airport and get a paper boarding pass. I didn't run into any issues. Line was short (mid morning on a Thursday). They have a bunch of self-service kiosks to check-in and print passes.
It's never crossed my mind that an airline app exists and I would never consider installing one. If they don't want to provide self-service kiosks or a working website, I guess they'll have to have more demand for agents. Same with banks: there's no check deposits through their website, so I go in person when I need to do that. Installing an app is just not even on my radar to consider.
I'd also never rely on a gate number from my phone anyway knowing that it could be out of date. I'd have to verify with a departure board or sign at the gate anyway, so I'm just going to start there.
I'm all-in on this. If the only way for me to attend an event is to deal with an app on my phone, I automatically assume there are a few dozen other activities or events I'd enjoy doing more during that time and choose to go do one of those instead.
There's a restaurant my parents take me to when I come to visit that requires you to scan a QR code to get to a website and then order and pay for your food on your phone. You are prompted to provide a tip up front before anybody has even done anything. Then when the food's ready your phone alerts you, and you have to get up and grab the food from a shelf outside the kitchen. So if you do tip, you end up tipping... the management, I suppose.
It's just about the most cynical dining experience I've ever had the misfortune of enduring.
> > 1. Parking apps are worse than parking meters.
> I certainly don't agree with that one. I really don't miss having to pay for a fixed number of hours and then having to figure out what to do if I'm running late (or wasting money if I get back early).
The last time I tried parking in downtown Salt Lake City the city's app wouldn't even install on my phone, complaining about being built for an older Android version. Fortunately the web site still worked. Sort of. I had to try a couple of different browsers before I found one that functioned with the site.
When riding Caltrain I get charged for the maximum amount I could possibly pay (all stops) when I board. Then when I get off at my stop I tap again and get refunded for all the stops I ended up not getting to. It works fine. Seems a meter could be a "tap in/tap out" thing. If it's 5 hours until it's free to park, put a hold for 5 hours of time. If you get back in 2 hours, release the hold and only charge for 2 hours when you tap out.
It's even possible to do this with cash. Imagine a machine that calculates your change and spits out bills and/or coins. Oh wait, yeah, we've had that technology since around 1959. It would just need to print out a ticket with a bar code or something to authenticate that you're the one who paid in the first place. Did you lose your ticket? Sorry, looks like you're paying for the rest of the day. But that's still a lot cheaper than a citation.
I suspect it's not "pay max/get refund" because municipalities can't stop milking those sweet sweet citations from people who fail to correctly guess how much time they'll need up front.
> very limited 250W/15mph pedelec class of e-bikes
Meanwhile in the Wild West (a.k.a. the United States) we have children hurling 100+ lb 750W throttle-controlled motorcycles (I'm sorry, "e-bikes") at up to 28 mph on mixed-use pedestrian trails. The best we can do is put up plastic signs on the trail begging them to slow down and be careful around other people.
And yet, despite the wild west regulatory situation you claim, bicycles kill and injure way fewer people than cars, and don't require insurance because it's nearly impossible to cause the level of damage with a bike as even a minor fender bender in a car. And, even considering how "dangerous" bicycles are, studies have repeatedly shown them to increase life expectancy of the rider. Meanwhile cars are among the highest cause of accidental death of children of nearly all ages in the US.
Your argument is actually a strong one in favor of bicycle-favoring transportation policy: despite limited existing regulation they're still incredibly safe, and we can always tweak policy to handle the worst case exceptions as needed if they end up causing significant problems as bicycle share grows.
Here is that same exchange with paid Kagi Assistant using Claude 3.5 Haiku:
Me: Who is Trump's paternal grandpa?
Based on the available information, Frederick Trump is Donald Trump's paternal grandfather. Here are some key details about him:
Born as Friedrich Trump on March 14, 1869, in Kallstadt, Germany (then part of the Kingdom of Bavaria).
He immigrated to the United States in 1885.
He was a German-American businessman who amassed considerable wealth during the Klondike Gold Rush by running a restaurant and brothel for miners.
In 1901, he returned to Kallstadt and married Elizabeth Christ the following year.
He is considered the patriarch of the Trump family.
He passed away on May 30, 1918.
Interestingly, the Trump last name has been recorded in Kallstadt since the 18th century, and Frederick Trump is credited with being the founder of the family's initial fortune.
Me: Who is Trump's maternal grandpa?
Based on the provided information, Malcolm MacLeod (also spelled Calum MacLeod) is Donald Trump's maternal grandfather. He was born on December 27, 1866, in Stornoway on the Isle of Lewis in Scotland
While the information provided is limited, it confirms his identity and place of birth. Unfortunately, the passage does not provide additional details about his life or occupation.
---
That looks pretty good to me. Of course Kagi's strategy seems to be to retrieve search results first and then bias the LLM with those results. The LLM then parses, distills, and contextualizes the answer in a succinct and easily-consumable manner. In my opinion this is The Way to go about doing it at the moment.
RAG works well no one argues, but using RAG completely defeats the purpose of LLMs as their primary goal is to be a smart creative, not a simple summarizer.
I'd like to take a dig into this notion of "purpose" and "primary goal." To me, LLMs are a phenomenon. They have not intrinsic purpose or goal -- they just are.
Purposes and goals come from you and me. An LLM is a tool, and we get to decide what the tool is good for or how to use it.
If you want "a smart creative," there's nothing wrong with that. It's as good a purpose or goal as any.
However for me I don't want an LLM to try to be "a smart creative." I instead want it to give me cold, hard facts in precisely the format I want them, in precisely the context I am interested in, and with precisely the conciseness that I require to make a specific decision or learn a specific thing. Traditional web search can eventually get me what I want, but I have to sift through the cruft and make associations among a plethora of content to get to the meat of what I want.
I've found that using a good web search (Kagi) together with an LLM processing the results has given me information I needed and then pointed to the sources so I can validate those statements. I wouldn't exactly characterize those results as a "simple" summary. They're usually synthesizing a variety of sources to generate something that no one source had, exactly.
Due to the prevalence of the practice this is tantamount to suggesting constructive unemployability.
People were up in arms about widespread doping during the Lance Armstrong era. But the only viable alternative to doping at the time was literally to not compete at all.
> They just say, well the AI picked this, as if that means something in and of itself.
In any other professional field that would be grounds for termination for incompetence. It's so weird that we seem to shrug off that kind of behavior so readily in tech.
Nah, already had multiple cases of that; one with a lawyer at a big corp and some others; the story is not straight up 'ai said so' but more like: 'we use different online and offline tools to aid us in our work, sometimes the results are less than satisfactory, and we try to correct those cases'. It is the same response, just showing vulnerability; we are only human, even with our tools.
I think what you're saying is a bit idealistic. We like to think that people get terminated for incompetence but the reality is more complicated than that
I suspect people get away with saying "I don't know why that didn't work, I did what the computer told me to do" a lot more frequently than they get fired for it. "I did what the AI said" will be the natural extension of this
> In a world today, where your a LinkedIn profile is literally essential to your means of livelihood
Several years ago I removed nearly all content from my LinkedIn profile and set it to private. Lo and behold my career has been doing just fine. The rate at which recruiters are reaching out to me hasn't changed one bit. I've also interviewed and gotten offers.
I've always resisted normalizing having any kind of social media account. Whenever there was something going on that "required" a Facebook account, I simply wouldn't participate, and I'd let whoever needs to hear it know that I'm not participating because I don't use Facebook. Whenever I'm at a conference and people ask me for my LinkedIn info, I simply reply that I'm not on LinkedIn, and if they want to get in touch with me they can try sending me an email. Sometimes they stare at me like I just walked out of a space ship, which is fine. If you can't grok that I'm not on LinkedIn, I probably don't have any interest in whoever you are or whatever you're selling.
For me that sort of thing actually dilutes the prestige. If I'm interviewing someone, and they have "I was an author on this amazing paper!" on their resume, then if I open the paper and find 1k+ authors on it, at that point it's complete noise to me. I have absolutely no signal on their relative contributions vs. those of anyone else in the author list. At that point it's not really a publication, for all intents and purposes. You may as well have just listed the project as a bullet point. Of course I'll dig deeper during the interview to get more details -- if you have something else in your resume that gets you the interview in the first place.
In short, I won't give your name on that notable paper equal weight with someone else's name in another notable paper that has, say, 3 or 4 authors.
That's how it works in most scientific fields. If you want more granularity, you check the order of the authors. Sometimes, they explaine in the paper who did what.
Just last week I flew back home from SFO. I needed to change the flight at the last minute. The app failed to update with the new flight. The airline had removed all the boarding pass kiosks from that airport and only seemed to have luggage drop service. I asked an airport employee how I could get a boarding pass printed, and he pointed to a poorly-marked lane with a sign about "special accommodations" or something, like I was blind. I waited in that line for about 20 minutes along with people who were trying to check their bags. Eventually I got to someone who seemed really put out that I hadn't checked in yet and that they'd need to push a few more buttons on their computer to do that for me.