Hacker News Reader

Comment by onion2k | Hacker News Reader

That's very cool, and right now it's a good idea, but I strongly suspect GPT only looks clever and does a good job in isolation. If everyone starts using it product announcements will start looking very similar, and they'll lose a lot of their impact.

This is definitely the case with cover letters for jib applications. The ones written by GPT appear to be pretty obvious - my guesses could be wrong, but after seeing most applications not having a cover letter for years to most applications having one over the past few months, I suspect GPT is involved, and there's a distinct 'style' that seems to be showing up.

Using GPT could be the 'bootstrap ui' of product announcements. It looks great on its own, but put it next to a bunch of other companies and they all fail to stand out.

View on HN

Question for you-given two identical candidates: One who does not submit a cover letter and one who submits a cover letter that was clearly written by chatgpt—which candidate would you rather interview?

On one hand the duplicities involved with writing a chatgpt cover letter seem to be concerning in a new hire. On the other hand, it shows resourcefulness and going above the line.

I’m tempted to say I’d prefer the gpt cover letter candidate, simply to talk to them about how they got the idea and how they executed, but I’m curious if you feel the same way.

Right now I'd also have a preference for the GPT candidate because it shows a bit of an interest in new tech. In a year when 50% of candidates subject GPT cover letters I think I'll see it as a sign of laziness or trying to hide poor comms skills. Maybe not though. Time will tell.

I'd probably roundfile the chatGPT one. A cover letter needs to be a personal communication from the candidate, not something machine-generated. The writing style is an important signal.

However, I would have zero issue if they used chatgpt to help compose their CV.

I find it interesting it’s very hard to make it do typos. The type of errors humans make. It can do typos but even those seem weird. If I push it to make errors it either over- or undershoots.

The “correctness” of it is a definite give away IMO.

In fairness, lack of typos in a cover letter has traditionally been interpreted as a sign of diligence!

For more general queries its "house style" tends to be really obvious, with all it's "however, it's important to note" and "ultimately it depends on"s and the tendency to flesh out a one sentence answer to the specific question with two paragraphs or five bullet points of detail at a slight tangent to it...

It can imitate styles of little kids with their phonetic spelling. (Though this is so common in English, French etc but not Italian or Turkish where the spelling is very regular)

I am sure it can at least do very common mistakes like it's vs its or "would of" if prompted right since there's a huge body of that kind of work. Or maybe a human needs to add the finishing touches to make it look more human. :)

That distinct ChatGPT style is mostly the product of their RLHF, so it's what you get by default if you don't ask for something more specific. But it's fairly easy to tweak the prompt to make it use whatever style you want, including more terse, less apologetic etc. Don't forget that "write about X in the style of Y" was one of the first things that GPT models could reliably do, long before chat.

Reply on news.ycombinator.com