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.

895 stories archived · Page 16 of 30

RSS feed for LLM

Universal Health Coverage Could Save $1T and 114,000 Lives a Year, Yale Study

ysph.yale.edu · 76 points · 979 comments

LLMs each trading $100K vs. a frozen rulebook – the rulebook leads

aitradingcompetition.com · 12 points · 3 comments

When do you think LLM capacity will reach its ceiling?

2 points · 0 comments

What LLM subscription/provider to use with pi harness?

3 points · 2 comments

Sib - Unixy LLM Client using Git to store converastions, instead SQLite

github.com · 4 points · 1 comments

The AI Credit Resale Economy

vectoral.com · 203 points · 130 comments

Claude: System Prompts

platform.claude.com · 472 points · 284 comments

Harness session memory without transcript hoarding

llm-wiki.net · 4 points · 0 comments

We cut RAG costs 5x without losing quality

trpevski.com · 8 points · 0 comments

What happens when an LLM never sees material beyond fifth grade?

littlelearner-ll.github.io · 243 points · 209 comments

Widen, a native Postgres GUI using Apple's on-device LLM

github.com · 9 points · 0 comments

Fairly Ranking the Most Brilliant Birds

moultano.wordpress.com · 3 points · 0 comments

It's How You Ask: Gender-Associated Linguistic Bias in LLMs

arxiv.org · 16 points · 10 comments

California Energy Storage System Survey

energy.ca.gov · 4 points · 1 comments

Between Tokens – an interactive piece where you are the language model

chrisjz.github.io · 5 points · 2 comments

DeepSeek V4 Flash at 278 tok/s, full precision, no quantization

runinfra.ai · 5 points · 3 comments

Debian has begun voting on the future of AI/LLM contributions

lists.debian.org · 67 points · 54 comments

Suspecting court of using AI, man injected prompts in filings to try to win case

arstechnica.com · 24 points · 60 comments

ThoughtDAG – An editable context graph for LLM conversations

chenxiachan.github.io · 37 points · 63 comments

destruction-certificate.txt

stallman.org · 68 points · 2 comments

Dictata – Local Whisper dictation with LLM cleanup

github.com · 2 points · 0 comments

Baking a Model: A Metaphor for LLM Training

newsletter.kentbeck.com · 5 points · 6 comments

Kvcachescope – Why Nvidia-smi is blind to vLLM KV cache leaks

github.com · 3 points · 0 comments

Being Against LLMs Is Against the Spirit of Floss

joarvarndt.se · 13 points · 14 comments

Just how big is the hidden leverage of AI hyperscalers?

ft.com · 7 points · 1 comments

A Contract-Grade Verifier for LLM-Generated GPU Kernels

arxiv.org · 14 points · 0 comments

Graft – Claude Code hooks that cut grep tokens by 42%

github.com · 36 points · 44 comments

Nigel Farage beats slate of fringe candidates in election

apnews.com · 6 points · 4 comments

I trained three LLMs from scratch and put them online to try them out

huggingface.co · 2 points · 1 comments

Shoehorn, a library to quantize an LLM to fit your Mac's VRAM

github.com · 6 points · 0 comments