All topics

LLM stories

Large language models have moved from research curiosity to production infrastructure. This topic focuses on LLM APIs, fine-tuning, RAG pipelines, agent frameworks, and the economics of running models at scale.

HN discussions here tend to be unusually practical — benchmark comparisons, cost breakdowns, and real deployment war stories from teams shipping LLM features.

889 stories archived · Page 6 of 30

RSS feed for LLM

Top mathematicians are outraged by OpenAI's methods

economist.com · 96 points · 20 comments

Extension to filter LLM written articles

hnslop.nilsherzig.com · 2 points · 3 comments

Rapidly scaling online storage to serve over 1B ChatGPT users

openai.com · 9 points · 0 comments

Token Bills, Exhausting Change, AI Thesis Crack, Automating Broken Systems

age-of-product.com · 5 points · 0 comments

Meta says it's changing AI suggestions after posing invasive personal questions

theverge.com · 5 points · 0 comments

Raggy – A lightweight CLI tool for RAG over local documents

github.com · 4 points · 3 comments

Bastiontrace – Forensics for prompt-injected AI agents

github.com · 2 points · 0 comments

What is the average number of hops in your social network to 9-11 death?

2 points · 6 comments

RTK reports token savings, but our cost benchmarks disagree

quesma.com · 26 points · 84 comments

Mining Qwen 3.8 reasoning trace for prompt/skill evaluation

olegivye.com · 4 points · 0 comments

DeepSeek and Moonshot were quietly relaying customer prompts to Claude

twitter.com · 4 points · 2 comments

LLM Visualizer – Build a Transformer from Scratch

jayvisaria.github.io · 13 points · 4 comments

Setting up OpenCode with Ollama and sbx on Mac

tensorsandtokens.com · 10 points · 14 comments

News observability site tracks coverage by party lean/distraction/etc.

pressaudit.org · 3 points · 0 comments

I created a translation service prompt

github.com · 2 points · 1 comments

Cognition's SWE-2 achieves 92.8 on Terminal-Bench 2.1

tokenstead.ai · 12 points · 27 comments

Nola – a TypeScript superset where LLM inference is a language feature

nola.sh · 2 points · 2 comments

Turn wire protocols into structured statements LLMs can understand

4 points · 0 comments

MultiMatte, a Promptable Image Background Removal Model

usefeyn.com · 10 points · 8 comments

Post-graph-RAG – your RAG still thinks the old CFO is the CFO

github.com · 2 points · 0 comments

Keynote: Linux in the Land of LLMs – Greg Kroah-Hartman [video]

youtube.com · 3 points · 0 comments

Calmscroll – a reader that shows the current paragraph in the library

calmscroll.com · 3 points · 0 comments

Pragma Twice – A dystopian sci-fi themed programming game

bryanpg.com · 2 points · 0 comments

Practical Agentic RAG patterns implemented with LangGraph

github.com · 7 points · 7 comments

Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning

arxiv.org · 3 points · 0 comments

Training a 3.8B LLM to 0.384 CORE for $998 – Hugo Vergnes

hugovergnes.github.io · 32 points · 20 comments

I Came, I Prompted, I Left Part 1: Building a Hypervisor for the MacBook Neo

codyho.dev · 12 points · 6 comments

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

arxiv.org · 4 points · 0 comments

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

arxiv.org · 33 points · 15 comments

Software Licenses that prevent LLMs from training on open source?

4 points · 5 comments