zlacker

[parent] [thread] 7 comments
1. potato+(OP)[view] [source] 2022-12-12 05:06:29
How could ChatGPT generate your perspective for you?
replies(2): >>xvecto+H >>mherde+b3
2. xvecto+H[view] [source] 2022-12-12 05:13:02
>>potato+(OP)
It doesn't generate the perspective (usually) but rather turns it into a reply.
3. mherde+b3[view] [source] 2022-12-12 05:39:06
>>potato+(OP)
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+c6 >>IncRnd+L6 >>burnis+U7 >>xxs+Lf
◧◩
4. fleshd+c6[view] [source] [discussion] 2022-12-12 06:13:39
>>mherde+b3
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+8a
◧◩
5. IncRnd+L6[view] [source] [discussion] 2022-12-12 06:18:06
>>mherde+b3
Those are entirely "fluff" comments, devoid of substance or example.
◧◩
6. burnis+U7[view] [source] [discussion] 2022-12-12 06:28:09
>>mherde+b3
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.

◧◩◪
7. Kuraj+8a[view] [source] [discussion] 2022-12-12 06:49:41
>>fleshd+c6
Which is how I often feel reading comments on HN to begin with.
◧◩
8. xxs+Lf[view] [source] [discussion] 2022-12-12 07:52:14
>>mherde+b3
>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.

[go to top]