Absolutely. It's one of my all time favourites stories and this is pretty much the reason why. I wish my users gave me such specific steps to reproduce!
What's my recent annoyance is that users will describe their problem in great detail if they are talking to LLM, yet same people make just as shit support tickets as before
(1) disguise as an LLM to have them give better problem descriptions to you
(2) provide an LLM for your users that lets you read their chat to understand their problem
and:
(3) try to understand why they are communicating differently to an LLM. Immediate replies? Different feelings knowing they don't talk to a human? Genuinely better help? Not getting treated as stupid?
All or none of these may be true, but if it's consistent behaviour then there is a reason for it.
your dream is coming true - most SMBs are quickly moving to have LLMs as their Level 1 support anyway. Makes sense unf, too many people fail at writing the proper ticket.
I should guess it is about liability more than anything else. They want to advertise and sell to children, but they don't want to be taken to court about it. Makes a tonne of sense from a profit perspective, especially as people under ~25 years of age are more susceptible to impulsivity and addiction due to the developing prefrontal cortex. From a sales perspective, the younger the better (as any parent can confirm).
I had a crack at reading the first Game of Thrones novel (I think it's just called A Game of Thrones) but my brain seems to be in non-fiction mode at the moment. I think I'm drawn to a kind of sweet spot halfway between "related to my everyday experience" and "removed from my everyday experience" - not sure I could read about programming or business at the moment, though I also haven't tried.
"If a SMTP mailer trying to send email to somewhere logs 'cannot contact port 25 on <remote host>', that is not an error in the local system and should not be logged at level 'error'."
But it is still an error condition, i.e. something does need to be fixed - either something about the connection string (i.e. in the local system) is wrong, or something in the other system or somewhere between the two is wrong (i.e. and therefore needs to be fixed). Either way, developers on this end (I mean someone reading the logs - true that it might not be the developers of the SMTP mailer) need to get involved, even if it is just to reach out to the third party and ask them to fix it on their end.
A condition that fundamentally prevents a piece of software from working not being considered an error is mad to me.
There is no "connection string" in mail software that defines the remote host. The other party's MX records do that. If you are sending mail to thousands of remote hosts and one is unreachable, that is NOT a problem a mail administrator is going to be researching or trying to fix because they cannot, and it is not their problem. Either the email address is wrong, the remote host is down, or its DNS is misconfigured. This happens constantly all day long everywhere. The errors are reported to the sender of the email, which is the person who has the problem to solve.
OK yeah I think I see what you're saying, if the SMTP mailer is a hosted service and we're talking about the logs for the service itself then failed connections are not an error - this I agree with. I also wouldn't be logging anything transactional at all in this case - the transactional logs are for the user, they are functionality of the service itself in that case, and those logs should absolutely log a failure to connect as an error.
It doesn't matter if it is a hosted service or if its just your local mail transfer agent, every "SMTP mailer" works the same way. There are lots of ways to send email that don't involve a locally administered SMTP mailer (such as an API which indeed has a connection string to a hosted service) but none would be described with that term.
Exactly this, a remote error may still be your problem. If your SMTP mailer is failing to send out messages on behalf of your customer because their partners' email servers cannot be reached, your customer is still going to ask you why the documents never arrived.
Plus, a remote server not being reachable doesn't say anything about where the problem lies. Did you mess up a routing table? Did your internet connection get severed? Did you firewall off an important external server? Did you end up on a blacklist of some kind?
These types of messages are important error messages for plenty of people. Just because your particular use case doesn't care about the potential causes behind the error doesn't mean nobody does.
This is actually pretty much as done as it's going to be (could use some nicer UI feedback, i.e. how you actually use the app) - it is actually just a demo for an effort I undertook to mod Datastar to support nested web components. I am writing it up as we speak!
Instructions: you have to answer three questions; each one will auto-submit once your response goes over 100 characters; the answer to the third question is your "post". It's a proof of concept of a friction intervention for social media to encourage slow thinking before posting (and hopefully reframing negative experiences in the mind, it's kind of dual purpose).
Point of curiosity: the community prediction is, presumably, an arithmetic mean, but I argue that is not a good model for a dataset that almost certainly gets more dense closer to the present, creating a gradient out into the future. It would be great to see the geometric mean as well.
This is actually a surprisingly effective way to get a broad range of feedback on topics. I realise this was built for fun, but this whole discussion dynamic is why I value HN in the first place - it never occured to me to try and reproduce it using LLMs. I am suddenly really interested in how I might build a similar workflow for myself - I use LLMs as a "sounding board" a lot, to get a feeling for how ideas are valued (in the training dataset at least).
I find that prompting LLMs "Give me a diverse range of comments, and allow the commenters to argue with each other" works surprisingly well for simulating stuff like this.
Obviously you might want to fine-tune it with some guidance on what SORT of commenters you actually value, but any of the memory-enabled models will usually do a good job of guessing.
Also tends to shake it out of a lot of the standard LLM-speak ruts as it's trying to emulate a more organic style
It's funny, I have never thought of it this way, but, reflecting, I realise the way I do think about it is very similar. Whenever I have to justify a subscription on JetBrains or hosting or what have you, I always just ask myself: will this bring me joy? Specifically will it bring me as much joy as e.g. a Netflix subscription? Very easy to justify then.
To be fair, I used to smoke cigs, and drink heavily, which are both very expensive habits. I've since quit those (they weren't bringing me joy) but the benchmark is the same.
So it's fascinating reading this looking at the screengrabs of the "original" versions... not so much because they are "how I remember them" but indeed, because they have a certain nostalgic quality I can't quite name - they "look old". Presumably this is because, back in the day, when I was watching these films on VHS tapes, they had come to tape from 35mm film. I fear I will never again be able to look at "old looking" footage with the same nostalgia again, now that I understand why it looks that way - and, indeed, that it isn't supposed to look that way!
Baader-Meinhof complex in action: I have _just_ ordered a book of Rovelli's (Reality is Not What It Seems - https://en.wikipedia.org/wiki/Reality_Is_Not_What_It_Seems), it should be in my hands by the end of the week. I am fascinated by the ongoing work in quantum gravity, it's tantalising by its nature.
This is a great interview and I must say I like the man a lot more than I did before. He has articulated something here that I have long felt: that it is as important in politics as it is in philosophy or theoretical physics to be able to state one's assumptions, to suspend one's assumptions for the sake of argument and to drop/change one's assumptions in the face of evidence.
I feel like this is a vital skill that we, as a society, need now maybe more than ever, in literally any field in which there is any meaningful concept of "correct" (which I think is most fields). I also think it's a skill you basically learn at university - and that that is a problem. I don't know what an approach to cultivating it more widely would look like.
reply