Yes, thank you so much. I totally wanted and have time for a scavenger hunt + jigsaw puzzle. Clearly you understand enough of the issue to know that I need to handle it but can’t be bothered to spend 45 seconds to summarize the relevant bits.
You must log in or register to comment.
- i_stole_ur_taco@lemmy.caEnglish1 month
That’s when you reply and fixate on completely the wrong part of the thread. Teach them for not setting the right context.
- Tolookah@discuss.tchncs.deEnglish1 month
Reply back: several questions, see my reply in red and ask one question
- 1 month
Bonus “Mildly infuriating”:
Ask 4 bullet-point questions in an email, they only answer one of them and ignore the rest.
- jtrek@startrek.websiteEnglish1 month
I can’t tell if people who do that kind of thing are lazy and malicious, actually stupid, or stressed beyond their capacity to be decent.
I do think a lot of people are actually only semi literate, and asking them to write is legitimately difficult and embarrassing for them.
1 monthi am so fucking thankful that i have never used email for any kind of work
- 1 month
A few times, people have just forwarded an email thread to me, without ever typing any words into it, not even, “see thread”. Straight into the bin go those threads. So f*ing lazy!
- HubertManne@piefed.socialEnglish1 month
honestly I feel the same about people just putting links or media into a post. I get it. Its me. I come here for communication. I want to know at the very least why you felt something was important enough to post. Why did they like it. Why I should like it. Does it have meaning to them. Is it just a laugh. etc. I kinda wish I could block all posts that did not have about as much body as you have up there.
Valid. I hate link only posts. Especially when the link is to a video with clear clickbait titles. I tend to just keep scrolling. I would love a setting to block posts that are only a link and no details.
This drives me crazy. At least give me a description for your YouTube link so I can decide if it interests me. “Check this out” isn’t good enough, give me a bloody reason.
No, no it is not.
It is a case for smarter client software, if anything. Deterministic smarter client software that just shows you the context instead of making it up.
- BlameThePeacock@lemmy.caEnglish1 month
Deterministic software can’t summarize a long email thread, or that would already exist as a feature.
We can’t even get deterministic software to ask people what they’re calling their cellphone provider about well enough to route them on anything more than broad keyword matching.
This anti-ai shit is nauseating. Businesses that rely on it too much are going to fail, but businesses that refuse to use it at all will get out competed over the next decade.
It’s a tool like any other, use it where it’s strong. Like summarizing a fucking email thread. Modern models and integrations are not just randomly hallucinating topics of conversation in a single email thread at this point, we’re well past that level of incompetence.
My whole point was that it shouldn’t be a summary, it should be the actual context, in the actual words of the actual people who actually wrote it. Not what the statistical wordsharter pretended to compress it down to.
– Frost
- BlameThePeacock@lemmy.caEnglish1 month
Why? We already write summaries as humans for long concepts and ideas. Executive summaries, abstracts, conclusions, we’ve been doing this kind of language compression as humans forever.
Emails chains can often contain out of sequence information, repetitions, contradictions, disagreements, and just the stupidity of human communication in general.
Because a person writing a summary actually understands what they read and wrote the summary based on that.
LLMs don’t. It’s literally fancy autocomplete. That’s all it is. It’s really fancy autocomplete, but it doesn’t actually understand anything.
– Frost
- BlameThePeacock@lemmy.caEnglish1 month
And yet it produces better summary output than many humans I’ve had the (dis)pleasure of reading the work of.
You’re assuming because it doesn’t function the same way as a human that the output can’t be equal or better. That’s simply not the case at this point in this type of task.
Autopilot in airplanes doesnt fly like a human, and yet its installed and running on almost every passenger flight in the world.
Autopilot in planes also isn’t an automatic pilot. All it does is the bare minimum of “keep the plane level at this altitude/climb rate and/or heading this direction” while you focus on other things (unless you get distracted in the wrong place and fly into a mountain). Some get a little fancier than that, but still.
It doesn’t replace the pilot and it’s not even trying to replace the pilot.
Oh and you know what happened when pilots got too used to following the line on their display instead of actually using their brains and reacting to the situation? Planes started crashing. They had to actually dial back on the automation somewhat. https://99percentinvisible.org/episode/children-of-the-magenta-automation-paradox-pt-1/
– Frost
- BlameThePeacock@lemmy.caEnglish1 month
The same way it knows anything, by looking at all of the tokens.
are you taking the piss or do you actually think that’s a good answer?
