Hacker Newsnew | past | comments | ask | show | jobs | submit | vgr-land's commentslogin

I’ve been thinking a bit on how to improve discourse between disagreeing people and how the quick response style of comment sections don’t lend themselves to serious debate.

One idea I have is to mimic Lincoln–Douglas debates where two people debate each other in a fixed format and with structured time for rebuttal. The hope being by slowing down rebuttal the response becomes more mindful.

In general though I think its the speed and low quality of response leading to dissatisfaction of comment platforms.


The comparing 2025 with the 2023 and 2024 versions of the article is also an interesting snapshot in the state of tech journalism.

(Also yes my Brother printer is just fine and turning 7 years old)

https://www.theverge.com/23642073/best-printer-2023-brother-...

https://www.theverge.com/2024/4/2/24117976/best-printer-2024...


These are really interesting to read in order. The LLM output at the end of each shows how they've gotten better and stayed the same. Output is all formulaic just following slightly different formulas. I shall excitedly wait another year to see what is possible in 2026 and if everyone is right by 2027 the LLM will be the author of the piece including human written content for padding at the end.

(Also yes my Brother printer has worked great over the past 10 years. I even had to buy new toner and have replaced it with a third party toner twice so far.)


LLMs make it much easier. Then you get all the benefits with few of the frustrations


!


https://news.ycombinator.com/item?id=45006098

I used LLM (gpt o4-mini) for developing a blog template. Overall it did a good job especially with logic loops

Otherwise xml messes up its outputs sometimes

I had to reset my context window frequently

It would do a bad job troubleshooting large sections of code


Probably abysmal

Since xslt is built dynamically in the DOM most crawlers don’t build the site and pick up the metadata.

Although I’m not convinced chasing SEO is a useful endeavor any more https://housefresh.com/beware-of-the-google-ai-salesman/

I wonder if AI crawlers would have the same problem and pass over the site


As long as the LLM crawler fetches the XML in the first place I assume it would be fine. Lighthouse is trying to score the rendered HTML, the LLM just needs to understand what's in the document and it can parse the XML directly.


Thanks for the suggestion I’ll dig into this, admittedly I haven’t worked with Atom so I didn’t consider it

A quick glance at Atom though says to me its worth an attempt to refactor.


For your possible interest, my own https://chrismorgan.info/atom.xsl is the most thorough Atom Feed Document stylesheet that I know of.

(I did also make an RSS version of it, https://temp.chrismorgan.info/2022-05-10-rss.xsl, including handling RSS’s stupid date format as perfectly as possible for some reason. It would actually be a useful guide for reversing that process, too…)

For maximum enthusiasm in this direction, make posts actual Atom Entry Documents. Will it benefit anyone? … well, I suppose it could be convenient for tooling to make a feed by just concatenating documents.


Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: