Hacker News Reader

Comment by partyficial | Hacker News Reader

the author can ask the same question - why should I write something if you're just going to use a LLM to summarize it ?

This is an unnecessary argument both ways. Whether you use a LLM or write it yourself or read it yourself (and then comment on it), you're putting your signature beneath it. I don't care whether you use your natural brain or an artifical brain (LLM)

View on HN

Because it's an asymmetric relationship? If you write something it can be consumed with value at many different levels, and an llm summary is valid. If we could trust llms to get the details right, creation of technical content would also be valid, but for now IME the editing and proof reading required outweighs any gains.

> the author can ask the same question - why should I write something if you're just going to use a LLM to summarize it ?

I wouldn't. LLMs don't summarize things very well. If you don't care if someone wrote it, and you don't plan to read it, why are you even here?

> you don't plan to read it

Not in full. I plan to read the LLM's summary. Most people could benefit from brevity.

author : writes the summary (prompt). LLM expands it to article.

reader : LLM summarizes the article. reader reads it.

both author and reader are free to use, or not use LLM. I don't see the big deal here.

Seems stupid.

But I don't use LLMs to summarise articles.

I don't care what you use. But if it reads or sounds like slop, I'm tuning out

Reply on news.ycombinator.com