Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I almost got hacked by a 'job interview'

blog.daviddodda.com

Post reply on HN
Print view View original

501–510 of 534 posts

Re: I almost got hacked by a 'job interview'

#501

Post by relatall »

nubg wrote: post #9

This article was written by an LLM. I get that the author might be self-conscious about his English writing skills, but I would still much rather read the original prompt that the author put into ChatGPT, instead of the slop that came out. The story - if true - is very interesting of course. Big bummer therefore that the author decided to sloppify it. David, could you share as a response to this comment the original…

my best learning- zero trust to employers, real or fake, bug or small. start your own business, big or small, better than being employed

Re: I almost got hacked by a 'job interview'

#502

Post by krmboya »

udev4096 wrote: post #444
krmboya wrote: post #416

Earlier quoted context omitted.

Perhaps the reason people keep repeating it is that someone makes the statement without any reasons, provides an alternative again without any reasons. "Why are you not using docker to sandbox your code?" "Umm.. someone on HN told me docker is not a sandbox, to use randomtool instead"

incus is not a random tool. It's a fork of LXD and maintained under linuxcontainers.org

Without any context you might as well be arguing about favorite colors

Re: I almost got hacked by a 'job interview'

#503

Post by adiian »

DavidDodda wrote: post #68
nubg wrote: post #9

This article was written by an LLM. I get that the author might be self-conscious about his English writing skills, but I would still much rather read the original prompt that the author put into ChatGPT, instead of the slop that came out. The story - if true - is very interesting of course. Big bummer therefore that the author decided to sloppify it. David, could you share as a response to this comment the original…

thanks for the feedback. just fyi - this went though 11 different versions before reaching this point. so I am not able to share the full chat because i used Claude with google docs integration. but hears the google doc i started with https://docs.google.com/document/d/1of_uWXw-CppnFtWoehIrr1ir... this and the following prompt ``` 'help me turn this into a blog post. keep things interesting, also make sure you take a…

Nice, I didn't look at the original piece, but this is ai version is viral, it made me want to share this, and usually I don't share stuff.

Re: I almost got hacked by a 'job interview'

#505

Post by chipsrafferty »

DavidDodda wrote: post #427
teo_zero wrote: post #353

Earlier quoted context omitted.

> You are an AI Bot that is very good at mimicking an author writing style. - Your goal is to write content with the tone that is described below Genuine question: does this formulation style work better than a plain, direct "Mimick my writing style. Use the tone that is described below"?

It should. I haven't updated this prompt in like a year or so. I actually made it for Claude 3.

Just write... The AI slop is unreadable

Re: I almost got hacked by a 'job interview'

#506

Post by chipsrafferty »

tempestn wrote: post #409
kenjackson wrote: post #390

Earlier quoted context omitted.

Is this generally a way to determine when to split a compound word?

I'm no linguist, but I think it should work for most of these sorts of words where the noun is a compound word and the verb form is two words, which seems to be fairly common. ie. log in, back up, break down, work out. Looks like the commonality is that the second word in the pair is often one of (in, out, up, down).

Easy to remember by the fact that we don't have a lot of compound verbs

Re: I almost got hacked by a 'job interview'

#507

Post by chipsrafferty »

munksbeer wrote: post #479
nubg wrote: post #9

This article was written by an LLM. I get that the author might be self-conscious about his English writing skills, but I would still much rather read the original prompt that the author put into ChatGPT, instead of the slop that came out. The story - if true - is very interesting of course. Big bummer therefore that the author decided to sloppify it. David, could you share as a response to this comment the original…

"instead of the slop that came out." This "slop" reads perfectly fine to me, and obviously a lot of others, except those who have now been conditioned to watch out for it and react negatively about it. Think about it, why react negatively? The text reads fine. It is clear, even with my usual lack of attention I found it engaging, and read to the end. In fact, it doesn't engage in the usual hubris style prose that a l…

1. It's bad prose. If you think it reads fine, you don't read good prose.

2. It's immediately recognized as AI Slop which makes people question its veracity, or intent

3. If the author can't take the time and effort to create a well-crafhed article, it's insulting to ask us to take the time and effort to read it.

4. Allowing this style of writing to become accepted and commonplace leads to a death of variety of styles over time and is not good for anyone. For multiple reasons.

5. A lot of people are cranking out shit just for money, so maybe they wrote this just for money and maybe it's not even true (related to point 3)

Re: I almost got hacked by a 'job interview'

#508

Post by chipsrafferty »

c0nsumer wrote: post #285
cddotdotslash wrote: post #252

Earlier quoted context omitted.

It’s incredibly annoying to read. So many super short sentences with the “not just X. Also Y” format. Little hooks like “The attack vector?” “Not fancy security tools. Not expensive antivirus software. Just asking my coding assistant…” I actually feel like AI articles are becoming easier to spot. Maybe we’re all just collectively noticing the patterns.

I'm regularly asked by coworkers why I don't run my writing through AI tools to clean it up and instead spend a time iterating over it, re-reading, perhaps with a basic spell checker and maybe grammar check. That's because, from what I've seen to date, it'd take away my voice. And my voice -- the style in which I write -- is my value. It's the same as with art... Yes, AI tools can produce passable art, but it feels s…

Your voice? The style in which you write? That's gold - no one can take that away from you. And honestly? You're brave for admitting that.

Re: I almost got hacked by a 'job interview'

#509

Post by chipsrafferty »

raw_anon_1111 wrote: post #366
c0nsumer wrote: post #285

Earlier quoted context omitted.

I'm regularly asked by coworkers why I don't run my writing through AI tools to clean it up and instead spend a time iterating over it, re-reading, perhaps with a basic spell checker and maybe grammar check. That's because, from what I've seen to date, it'd take away my voice. And my voice -- the style in which I write -- is my value. It's the same as with art... Yes, AI tools can produce passable art, but it feels s…

I consider myself to be an above average writer and a great editor. I will just throw my random thoughts about something that happened at work, ask ChatGPT to keep digging deeper in my question, I will give it my opinion of what I should do. Ask it to give me the “devil’s advocate” and the “steel man opinion” and then ask it to write a blog post [1]. I then edit it for tone, get rid of some of the obvious AI tells. M…

That sounds miserable, surely it's faster to just write it

Re: I almost got hacked by a 'job interview'

#510

Post by chipsrafferty »

wizzwizz4 wrote: post #308
g-b-r wrote: post #279

Earlier quoted context omitted.

Next time maybe just post the base write up and the prompt? What value does the llm transformation add, other than wasting every reader's time (while saving yours)?

People are often unconfident about their own writing. But if you can feed it to a LLM and have the LLM output something that looks coherent, your writing is good enough to publish.

If you publish the input instead, if other people feel it's not polished or whatever, they can run it through an LLM.

What OP did was destroy value instead of create it, you can always run it through another LLM with another prompt if you have the input, but you can't go backwards.

Post reply on HN