People don't like this because you move the responsibility of verification to the reader.
Does the program cheat? Does it just query a table is saved in some backend? Maybe, I don't know, you don't know, and since the author only pressed enter once no-one will know until/if someone runs into any issues.
When you can create information for free, and you want people to use this information you need to provide guarantees, proof, and understanding beyond what the autonomous model has done. Otherwise you just move the burden of verification to the reader.
did you edit it? did you fully read everything yourself and take out anything extra that didnt need to be in there like unnecessary comparisons and typical AI idioms? tweak the language to be less dramatic or emphatic about things that do not need emphasis?
AI is a great tool, but it is somewhere between a 3D printer and a CNC machine. it can make something smooth and easy to handle and maybe good enough for personal use but you would want to run it through some Finishing steps before giving its output to someone else. In some cases thats using the output as a mold for a full recreation and other times maybe its just sanding it a bit, smoothing out some rough spots and putting paint on it.
youre right not to care about if something was made by a human or a tool, but the full presentation of the content including editing is part of the content when it comes to a write-up.
I am not offloading anything. I need way more critical thinking than I ever needed before to review solutions proposed by my digital slaves to evaluate whether they are garbage or good.
If you think that having slaves means you don’t need to be a good administrator, then you are sorely mistaken.
It requires more brainpower than it ever did to manage a project the size what used to do a 100 people team. All on your own.
The fact that I am arguing with all of you here and not blindingly follow the narrative should tell you all you need to know about my critical thinking prowess.
- i can add and subtract 7 digit numbers effortlessly now
- i am still working on multiplication and division though but we ll get there slowly
- let me give you an example live
2949745
-
2947648
- my thought process to do this goes like this
- 1st 3 digits are same ignore
9745
-
7648
- 2nd step is to round off 9700 - 7700 = 2000, add 45 to it and it makes 2045 , we are still 52 short, add 50 to it and make it 2095, now add 2 and it becomes 2097
- see? no calculator needed
- i can do this faster than you can type the numbers above inside your beloved calculator
> People are increasingly getting fed up with slops like this -- you can see comments in HN discussions.
Why claim 'people' (plenty of people get value from satisficing) and even try to use 'see comments in HN discussions' as if there is something that actually documents that ie 'we all think it'.
I skimmed it and even skimming it I got value from (what some others here) call 'slop'. (The value was basically it gave me an idea of something I could implement and again I didn't have to study it or even understand everything (or agree) just seeing someone did that made me think about something I might want to do.
I dunno, you'll notice several people here saying that got value from it, despite others not engaging with it at all. If your filter is that you don't engage with anything you don't expect a priori to get value from (based on weak signals), you'll miss a lot.
it's not that it might help or not, it's more like,
"if an AI wrote this, that means I can generate the exact same text (or better) myself, and be _even more_ helped, whenever I'm interested in this topic, by using AI"
having a blog full of ai content is like having a web page that's a list of links to searches for random keywords on google: what's your contribution? picking a topic? is that anything?
That's only if you assume the human didn't have any control over what the AI wrote, and I think that's more and more a very wrong assumption. It's easy to have a lot of control over LLM output, and to use expertise to steer it (non experts steer the LLM in very different directions compared to experts). And the output being raw text, it's also very easy to edit and refactor it to say what needs to be said. Some people are even (unconsciously or not) adopting AI colloquialisms in their own writing. I think it's becoming very unclear where human and AI content begins and ends.
> having a blog full of ai content is like having a web page that's a list of links to searches for random keywords on google
What's any blog? A person just presses a bunch of buttons on a keyboard, is that anything?
I think you dramatically overstate the human contribution, but if it exists, it would be seen by the author sharing their prompts. I can see how that might prove embarrassing, though, if their contribution is minimal, so I can see why so few people do it.
> What's any blog? A person just presses a bunch of buttons on a keyboard, is that anything?
If it's a human writing it, sure: it's a unique contribution by somebody who put forth effort to help others.
If it's just LLM output, then you might as well have a blog posting the results of random math equations from your calculator. Was any significant human effort involved? Odds are no, but "authors" using LLMs are free to prove otherwise by providing their prompts.
