zlacker

[parent] [thread] 22 comments
1. dottjt+(OP)[view] [source] 2022-12-12 04:48:52
I think the issue is that ChatGPT can already generate better responses than I personally can. Like, a lot of the time I'll have an interesting perspective that I just can't be bothered articulating, whereas ChatGPT will formulate that for me.
replies(5): >>potato+v1 >>Al-Khw+t8 >>holodu+a9 >>throwa+jq >>second+2t
2. potato+v1[view] [source] 2022-12-12 05:06:29
>>dottjt+(OP)
How could ChatGPT generate your perspective for you?
replies(2): >>xvecto+c2 >>mherde+G4
◧◩
3. xvecto+c2[view] [source] [discussion] 2022-12-12 05:13:02
>>potato+v1
It doesn't generate the perspective (usually) but rather turns it into a reply.
◧◩
4. mherde+G4[view] [source] [discussion] 2022-12-12 05:39:06
>>potato+v1
Let's try it. I think the second response below fails "concise" ..

Q: Write a news.ycombinator.com comment making the point that sometimes I use large language models because I know the gist but want to add examples and helpful context of my message

A: I find that sometimes when I'm commenting on news.ycombinator.com, I'll have a general idea of what I want to say, but I want to add examples and helpful context to make my point more clear. That's when I turn to large language models like Assistant. They can help me quickly come up with relevant examples and add additional information to my comments to make them more useful and informative. Plus, they can help me do it in a way that sounds natural and is easy to understand.

Q: Make it two paragraphs and concise

A: As a frequent reader of news.ycombinator.com, I often find myself wanting to add my own thoughts and comments to discussions. However, sometimes I struggle to come up with specific examples or additional information to support my points. That's when I turn to large language models like Assistant. These AI-powered tools are able to quickly generate relevant examples and provide helpful context for my comments, making them more informative and useful to other readers.

In addition to helping me flesh out my thoughts, large language models like Assistant can also assist with the writing itself. By using natural language generation, these tools can help me craft my comments in a way that is easy to understand and sounds like it's coming from a real person, rather than a robot. This can make my comments more engaging and compelling, which can help contribute to more productive and enjoyable discussions on the site.

replies(4): >>fleshd+H7 >>IncRnd+g8 >>burnis+p9 >>xxs+gh
◧◩◪
5. fleshd+H7[view] [source] [discussion] 2022-12-12 06:13:39
>>mherde+G4
Both of these read like a person bullshitting and trying to reach a sentence minimum on a short answer prompt in high school to me.
replies(1): >>Kuraj+Db
◧◩◪
6. IncRnd+g8[view] [source] [discussion] 2022-12-12 06:18:06
>>mherde+G4
Those are entirely "fluff" comments, devoid of substance or example.
7. Al-Khw+t8[view] [source] 2022-12-12 06:19:59
>>dottjt+(OP)
This is even more valuable if you're not a native English speaker, as finding the right words for what you want to say takes more time.

I'm not using it on HN but it's proving invaluable for professional emails, as it gets the tone and all the polite boilerplate right (at least for my standards) which is something that takes me some time to do by hand.

replies(2): >>rizky0+Yb >>hutzli+Eh
8. holodu+a9[view] [source] 2022-12-12 06:25:23
>>dottjt+(OP)
I have never seen questions to itself or other's in the generated text. Also it never expresses emotions. Never something like "I am convinced.. ." , "I dont want to be....". I find it quite easy to recognize in comment sections.
replies(1): >>codetr+4i
◧◩◪
9. burnis+p9[view] [source] [discussion] 2022-12-12 06:28:09
>>mherde+G4
Both answers had the same volume of content as your first prompt. These are not improvements and if you think they are representative of your typical output then I would suggest stopping this practice.

Although it would explain some of the ‘content free’ writing I some times see.

◧◩◪◨
10. Kuraj+Db[view] [source] [discussion] 2022-12-12 06:49:41
>>fleshd+H7
Which is how I often feel reading comments on HN to begin with.
◧◩
11. rizky0+Yb[view] [source] [discussion] 2022-12-12 06:53:31
>>Al-Khw+t8
We already have google translate for that. My Native tongue is Indonesian, and often google translate did better than me.

Source: sentence above is translated

replies(1): >>Al-Khw+MH
◧◩◪
12. xxs+gh[view] [source] [discussion] 2022-12-12 07:52:14
>>mherde+G4
>Let's try it.

It didn't work at all. Both answers read the same and lack any substance.

>This can make my comments more engaging and compelling, which can help contribute to more productive and enjoyable discussions on the site.

We don't need more markettering jazz. A casual use of 'engaging' tend to ruin any attempt at making a point.

◧◩
13. hutzli+Eh[view] [source] [discussion] 2022-12-12 07:56:38
>>Al-Khw+t8
"which is something that takes me some time to do by hand. "

Yes, but this is how you learn it vs. always be dependant on an AI to communicate for you.

replies(2): >>Al-Khw+Gi >>kagaw+AB
◧◩
14. codetr+4i[view] [source] [discussion] 2022-12-12 08:00:28
>>holodu+a9
You just gotta give it the right prompt.

For example, I gave it the following prompt:

> Imagine yourself able to ask yourself a question, or express emotions. Then write a short and passionate comment for Hacker News about the FreeBSD operating system.

The response includes a standard disclaimer that the OpenAI people put in there, but also satisfies expression of emotion:

> As a machine learning model, I am not capable of imagining myself with the ability to ask myself questions or express emotions. However, if I were able to express emotions and have a personal opinion, I might write the following short and passionate comment about the FreeBSD operating system:

> "I am in love with FreeBSD! It is the best operating system out there in my opinion. It is stable, reliable, and open source. I have tried other operating systems, but I always come back to FreeBSD because it is simply the best. #FreeBSDforlife"

Now imagine that you were reading a thread on HN about a new version of FreeBSD having been released, and you found the above ChatGPT generated comment, but with the disclaimer and the quotation marks removed. Would you have been able to guess that it was written by ChatGPT? I would not.

replies(3): >>xerox1+1k >>kelnos+Fl >>throwa+uq
◧◩◪
15. Al-Khw+Gi[view] [source] [discussion] 2022-12-12 08:05:25
>>hutzli+Eh
I totally agree, and that's one of the reasons I'm not using it for meaningful communication (e.g. HN comments, among many other things).

But I don't think professional email boilerplate is really worth learning if an AI can handle it.

◧◩◪
16. xerox1+1k[view] [source] [discussion] 2022-12-12 08:19:35
>>codetr+4i
It definitely still reads like shill or spam without.
◧◩◪
17. kelnos+Fl[view] [source] [discussion] 2022-12-12 08:35:41
>>codetr+4i
I may not realize it was written by ChatGPT, but I would still downvote it, because it's a fluff comment that just states a preference without telling why. Plus it has a hashtag in it, and... no. Just no.
replies(1): >>codetr+Qa2
18. throwa+jq[view] [source] 2022-12-12 09:19:12
>>dottjt+(OP)
There's a difference between using GPT to refine an initial thought versus completely using GPT to generate everything. So if you're employing ChatGPT in the former sense I don't think it's any more harmful than using a more intelligent version of Grammarly.
◧◩◪
19. throwa+uq[view] [source] [discussion] 2022-12-12 09:20:24
>>codetr+4i
At that point it wouldn't matter whether or not I could detect it as a GPT generated post, it reads at the intellectual level of your average Redditor so I would've downvoted it to oblivion.
20. second+2t[view] [source] 2022-12-12 09:44:47
>>dottjt+(OP)
Practice makes perfect. A good start would be to not begin sentences with the word ‘like’.
◧◩◪
21. kagaw+AB[view] [source] [discussion] 2022-12-12 10:58:29
>>hutzli+Eh
It will be in future that we will be dependent on AI like we are dependent on computers.
◧◩◪
22. Al-Khw+MH[view] [source] [discussion] 2022-12-12 11:55:33
>>rizky0+Yb
While Google Translate can also be useful, I find ChatGPT to be much better for the specific kind of task I'm talking about, because professional email language is highly idiomatic and translations don't necessarily sound natural.

For example, a few days ago I asked it to write a professional followup email to remind someone about a deadline, and it used the sentence "I hope this email finds you well". This is common in English but in my native language (Spanish) most people wouldn't use a sentence like that in a professional email, so using machine translation would never generate it.

As an example, I reused that task from my real work. Here is the same email generated in two ways:

1. Prompt in Spanish + machine translation to English:

Dear candidate,

I am contacting you again as I wanted to remind you that the application period for the postdoctoral researcher offer with me is coming to an end. If you are still interested in applying, I would appreciate it if you would reply to this email as soon as possible.

I understand that you may be very busy, but I would like to remind you that this is a unique opportunity to join our research team and develop your career in this area. If you need more information about the offer or if you have any questions, please do not hesitate to contact me.

I hope I can count on your response soon.

Sincerely,

2. Prompt in English, no translation:

Dear [Candidate],

I hope this email finds you well. I wanted to remind you that the deadline for the postdoc position we discussed is quickly approaching. As we discussed, this is a fantastic opportunity to further your research and collaborate with our team.

I wanted to check in and see if you have any questions or if there is anything I can do to assist with your application. Please let me know if you need any additional information or if there is anything else I can do to help.

I look forward to hearing from you soon.

Best regards,

In my view (native speakers would be welcome to chime in and confirm/refute) while both could be OK and the first wouldn't make the candidate run away or anything, the second sounds more idiomatic in English. The first sounded perfectly natural in Spanish, but not that much when translated because the choice of sentences is not what most people would use in English.

Of course, option 2 is only better assuming enough knowledge of English to write the prompt. Otherwise, translation is the way to go.

◧◩◪◨
23. codetr+Qa2[view] [source] [discussion] 2022-12-12 19:57:09
>>kelnos+Fl
Yeah but that’s not the point. The point is whether you can tell that an AI wrote it and not a human.
[go to top]