News for hackers. Stuff that matters.
Re:RAG Is Simpler Than You Think by jrochkind1 on Wednesday August 26, 2026 @07:11AM (#49446941)
More LLM-generated text about LLMs.

Is anyone else actually finding it harder and harder to read LLM generated text? I find it quite tiring, my brain just does not want to get through it.

Re:RAG Is Simpler Than You Think by Planktonne on Wednesday August 26, 2026 @08:08AM (#49447570)
Your brain is incredibly adept at pattern recognition; it doesn't focus on LLM-generated text for the same reason it doesn't stare at wallpaper.

We've all learnt that it's not really communication, and so can be dispensed with.

Re:RAG Is Simpler Than You Think by EGreg on Wednesday August 26, 2026 @07:14AM (#49446966)
It’s largely because LLMs are reaching for many different types of adjectives or verbs in the same sentence, in a jarring way. While embedding it in a confidently declarative sentence. Everything sounds like some profound insight, dialed to an 11, but written as poetry. Especially those headings. With the short sentences.
Re:RAG Is Simpler Than You Think by allexander on Wednesday August 26, 2026 @07:15AM (#49446980)
I have to agree with you. Yet it is tiring, people don't even try anymore.
Re:RAG Is Simpler Than You Think by allexander on Wednesday August 26, 2026 @07:13AM (#49446959)
In the same boat here.
Re:RAG Is Simpler Than You Think by inigyou on Wednesday August 26, 2026 @09:00AM (#49448344)
Re:RAG Is Simpler Than You Think by jrochkind1 on Wednesday August 26, 2026 @03:09PM (#49454216)
VERY interesting, thank you! So it's not just me.
Re:RAG Is Simpler Than You Think by cpdomina on Wednesday August 26, 2026 @09:49AM (#49449141)
the biggest giveway is actually not the writing style, but the content

"using GPT-4o-mini for query rewriting" -> model from 2024, when RAG was trendy, and all the langchain, llama-index, etc, docs mentioned this specific model

Re:RAG Is Simpler Than You Think by timedude on Wednesday August 26, 2026 @11:01AM (#49450396)
GPT-4o-mini is still very relevant. It is a very capable model and very very fast and dirt cheap. Excellent for this type of stuff
Re:RAG Is Simpler Than You Think by j0selit0 on Wednesday August 26, 2026 @11:14AM (#49450608)
author here. at most companies I've worked for recently (F500) RAG is still quite trendy. this was what frustrated me a bit and motivated to write this article - along with other experiences that definitely relate with some of the folks in the comments above
Re:RAG Is Simpler Than You Think by cpdomina on Wednesday August 26, 2026 @12:29PM (#49451836)
what I implied is that in 2024 a lot was written about RAG, LLMs were trained on it, and that explains your gpt-4o-mini reference. the argument is that the article is ai slop, and that point is totally unrelated to name dropping fortune 500s references
Re:RAG Is Simpler Than You Think by polynomial on Wednesday August 26, 2026 @02:32PM (#49453673)
But it's "trendy"
Re:RAG Is Simpler Than You Think by j0selit0 on Thursday August 27, 2026 @04:53AM (#49461779)
sorry if it came across as name dropping - the point I wanted to make is actually that F500s are chasing RAG (as in pure semantic search without any care for chunking strategies, evals etc) instead of starting with the basics.

and for the record, my last employer was still using gpt-4o and gpt-4o mini last year. and they are an F500 (not that it means anything, just for context).

Re:RAG Is Simpler Than You Think by j0selit0 on Thursday August 27, 2026 @04:54AM (#49461786)
and for the record, my last employer was still using gpt-4o and gpt-4o mini last year. and they are an F500 (not that it means anything, just for context).
Re:RAG Is Simpler Than You Think by jrochkind1 on Wednesday August 26, 2026 @03:10PM (#49454227)
But you actually had an LLM write this article, no?
Re:RAG Is Simpler Than You Think by j0selit0 on Thursday August 27, 2026 @04:55AM (#49461794)
to be fully transparent, I used LLM to review my draft yes. and interestingly enough, this article had tens of thousands of more views and estimulated significantly more discussions than my other, non-LLM written articles. so there's that.
Re:RAG Is Simpler Than You Think by jrochkind1 on Thursday August 27, 2026 @01:14PM (#49468026)
So maybe it works! They are of course models distilling the best click-baity eyeball trapping engagement processes.
Re:RAG Is Simpler Than You Think by literallyroy on Friday August 28, 2026 @10:01PM (#49486228)
Why pretend? You mean your draft was the meat of the article and you had an LLM make it an article (sentences rather than bullet points?)

This is absolutely not a small draft review or edit.

Re:RAG Is Simpler Than You Think by alerighi on Wednesday August 26, 2026 @09:50AM (#49449162)
Everything that is generate from a LLM is shit, I don't know why people continue using it. I'm waiting for this bubble to explode once for all so we can return doing things in the sane way.
Re:RAG Is Simpler Than You Think by polynomial on Wednesday August 26, 2026 @02:31PM (#49453654)
The enshittification of the web, now powered by AI.
Re:RAG Is Simpler Than You Think by LukasWeber on Wednesday August 26, 2026 @03:19PM (#49454373)
"This is where the real trade-off lives – not cost, but speed."

That is where I stopped