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.
890 stories archived · Page 7 of 30
RSS feed for LLMSoftware Licenses that prevent LLMs from training on open source?
4 points · 5 comments
Google: Attackers are using prompt injection against coding agents
cloud.google.com · 6 points · 1 comments
FinOps for LLM Spend – why your bill has changed
2 points · 0 comments
My LLM eval cried wolf. Here's what I measured
digline.dev · 6 points · 0 comments
Maxxwell – The IDE for Optimal Tokenmaxxing
maxxwell.dev · 9 points · 8 comments
GuardRail, shell guards that stop Claude Code before it pushes to main
github.com · 5 points · 0 comments
Ctrlb-decompose: Strip the noise from logs before sending to LLMs
github.com · 13 points · 0 comments
Mark 1x-9B – a 9B model that answers with interfaces, not paragraphs
huggingface.co · 2 points · 0 comments
How I Prompt
thorstenball.com · 70 points · 13 comments
Estimate your AI CO2 footprint
llmfootprint.fyi · 3 points · 0 comments
Self-host open-source LLMs on AWS with scale-to-zero
github.com · 3 points · 5 comments
Would you hire a new engineer, or get 300k worth of tokens for the team?
3 points · 9 comments
A Harvard PhD Is Designing Schizophrenia Drugs in His Garage with ChatGPT
2 points · 3 comments
Are you leveraging Spec-Driven / Spec-Anchored development?
3 points · 3 comments
Object storage is all you need
tigrisdata.com · 65 points · 42 comments
Onboard device storage is kept low for these reasons
circuitbored.com · 4 points · 0 comments
Large language models develop novel social biases through adaptive exploration
openreview.net · 201 points · 116 comments
The universal programming language of LLMs
4 points · 9 comments
Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs
github.com · 185 points · 156 comments
Ollama stand in replacement, 2-4x faster, not just basic optimizations
github.com · 3 points · 0 comments
"Please Remove All Mannered Prose" and Other LLM Incantations
matthewritch.com · 13 points · 5 comments
LLM Attention Visualization
ishamf.dev · 177 points · 32 comments
Dragon Microkernel in Spark Ada
github.com · 2 points · 2 comments
Why I'm Not Excited About the Graphene OS and Motorola Partnership
podcast.switchedtolinux.com · 18 points · 59 comments
Super Smash Brothers Melee has been 100% decompilated with the help of LLMs
github.com · 6 points · 0 comments
Reservoir sedimentation diminishes water storage and coastal delta resiliency
nature.com · 3 points · 1 comments
Why human syntax breaks LLMs (and how to fix agentic coding)
4 points · 3 comments
Multi-Agents LLM Financial Trading Framework
github.com · 20 points · 81 comments
Clean Web-to-Markdown: Fast HTML Extraction for LLMs and RAG
markdown.usemy.cloud · 5 points · 0 comments
Prompting Is Dead in 6 Months. Andrew Ng, Stanford [video]
youtube.com · 16 points · 24 comments