Throwing AI-generated walls of text into conversations

Post by keybored » Thu, May 21, 2026, 3:24 PM UTC

Forgeties79 wrote: post #65

keybored wrote: post #46

Earlier quoted context omitted.

[flagged]

The problem with this logic, no matter the context where it’s deployed, is that you can always default to “you’re doing it wrong” no matter what case or situation is brought up. It’s an argument that is unfalsifiable no matter what because you can simply gesture to the person as the problem in literally any scenario. If I build a car and it consistently gets into wrecks at a rate 500x that of other cars, you can’t ju…

Post by SoftTalker » Thu, May 21, 2026, 3:30 PM UTC

digital_voodoo wrote: post #113

nikeee wrote: post #67

When I'm encountering some WoT like that, I'd like to have a button like "view source", but for "view prompt". Most ai generated messages or docs are unnecessarily verbose and just reading the prompt would suffice. I don't really get why some people seem to think that it's somehow better to have their bullet point prompt as a huge text. It just wastes my time. And probably only makes it look like it took more effort…

> I don't really get why some people seem to think that it's somehow better to have their bullet point prompt as a huge text Probably people who have never wanted to put the required thinking effort in a simple, structured response to a question, and now think that "a lot of words" magically solves that skill issue.

Post by Arainach » Thu, May 21, 2026, 3:33 PM UTC

u_fucking_dork wrote: post #108

AlecSchueler wrote: post #33

Earlier quoted context omitted.

And with a more broadly applicable example we could share the link with friends, family and coworkers who aren't on HN.

But then it wouldn’t have tickled the HN reader quite the same way and wouldn’t have gotten voted to the top. This doesn’t even need to be a website at all. This is pure slop designed in a pig lab for HN trough.

Post by SoftTalker » Thu, May 21, 2026, 3:34 PM UTC

bluGill wrote: post #72

SwiftyBug wrote: post #8

> Nobody writes essays in Slack I 100% write long texts in Slack. I always try to provide as much context as possible when reaching out to someone with a question or request.

Do you start every response off with "that is a great question"? I don't know any human who does. "that is a great question" is reserved either for really hard questions, or sarcasm. The majority of questions are not great, they are just things the asker needs a simple answer.

Post by nikeee » Thu, May 21, 2026, 3:40 PM UTC

jtbayly wrote: post #80

nikeee wrote: post #67

When I'm encountering some WoT like that, I'd like to have a button like "view source", but for "view prompt". Most ai generated messages or docs are unnecessarily verbose and just reading the prompt would suffice. I don't really get why some people seem to think that it's somehow better to have their bullet point prompt as a huge text. It just wastes my time. And probably only makes it look like it took more effort…

Except often the prompt is just the previous comment. In the example, the prompt would be "Should we use Redis or Memcached?" In that case, there is nothing beneficial about the prompt, but the answer could be boiled down to a useful recommendation (from an AI, not a person).