News for hackers. Stuff that matters.
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by nbstme on Wednesday October 01, 2025 @08:32PM (#45445224)
It's mind blowing. It's so simple, elegant and... effective! Grep+glob and a lot of iterations is all we need.
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by Analemma_ on Wednesday October 01, 2025 @08:37PM (#45445254)
We always suspected find+grep+xargs was Turing-complete, and now Claude is proving it.
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by nbstme on Wednesday October 01, 2025 @08:41PM (#45445278)
Exactly. AGI implies minimal tooling and very primitive tools.
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by SV_BubbleTime on Thursday October 02, 2025 @01:42AM (#45446646)
AGI implies that a system is financially viable to let run 24 hours a day with little to no direction.

No amount of find+grep+LLM is even remotely there yet.

Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by delusional on Thursday October 02, 2025 @01:41AM (#45446641)
That's one of the most nonsensical comments on all of hackernews. A Markov change could have wrote it.

What do you mean Turing complete? Obviously all 3 programs are running on a Turing complete machine. Xargs is a runner for other commands, obviously those commands can be Turing complete.

I haven't heard of anybody working on a _proof_ for the Turing completeness of xargs, and I think the only conference willing to publish it would be Sigbovik.

Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by hyperbovine on Thursday October 02, 2025 @05:22AM (#45447694)
Can’t tell which of these two comments is the joke …
Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by EdwardDiego on Thursday October 02, 2025 @07:13AM (#45448238)
It was a joke.