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.
29 stories archived · Page 1 of 1
RSS feed for LLMForeman, a self-hosted LLM gateway for cost aware model routing
github.com · 5 points · 2 comments
Germans turn to battery storage to shield against fossil fuel price shocks
euronews.com · 3 points · 0 comments
Reform UK leader 'in real trouble' against Count Binface
mirror.co.uk · 32 points · 19 comments
Chorus: A fast WAL for object storage
rockwotj.com · 5 points · 4 comments
Instant GraphRAG over any Postgres database
polygres.com · 5 points · 4 comments
Men's average testosterone levels have halved in last 50 years
theguardian.com · 66 points · 68 comments
LOL Storage Bug on Microsoft Windows 11 Could Eat Up 500 GB Disk Space
itsfoss.com · 12 points · 1 comments
Bike4Mind – open-core AI workbench; any model, agents, RAG, self-host
github.com · 3 points · 2 comments
What is your AI harness that lets you switch LLM models easily?
8 points · 8 comments
PL/Ruby: Ruby as a procedural language for PostgreSQL (functions, triggers, SPI)
github.com · 6 points · 0 comments
I wrote a 1-bit WebGPU runtime to run a 1.7B LLM in the browser
aidekin.com · 5 points · 2 comments
Baerly-storage, a document DB that runs per request, no DB server
github.com · 16 points · 1 comments
Tracking GenAI cost and endpoint fragility so app teams don't have to
llmintel.ai · 2 points · 0 comments
Are LLMs slowly making companies dysfunctional?
6 points · 3 comments
I built a free website that makes LLM prompting easier in 40 languages
enlive.inc · 3 points · 1 comments
Signal for LLM – The Modulator Architecture (Theory Complete)
divinecanon.github.io · 2 points · 0 comments
Reinforcement Learning with Metacognitive Feedback Elicits Uncertainty in LLMs
arxiv.org · 12 points · 1 comments
Shadow Web – Cut 64–97% of web page tokens for LLM agents
github.com · 2 points · 0 comments
A little cat that counts your tokens (Claude and codex)
jpthecat.com · 3 points · 0 comments
Onboard CLI uses LLM to filter out nodes and AST to visualize codebase
github.com · 2 points · 0 comments
RagPack – Lightweight self-hosted RAG infra for startups
github.com · 2 points · 0 comments
BurstyRouter: local LLM first then burst to end-to-end encrypted LLM
github.com · 2 points · 0 comments
I made the Chrome Dino Game editable by your AI prompts
vibedino.com · 7 points · 0 comments
An unmetered LLM API–$6/month, no token tracking, no limits
yolo-auto.com · 12 points · 13 comments
Sidenote – comment on your rendered blog, an LLM writes the Git diff
github.com · 9 points · 0 comments
I Wasn't Allowed Prompting ChatGPT During My Chalk Talk: This Is Discrimination (2025)
inpreparation.substack.com · 233 points · 141 comments
Is anyone experimenting with different ways of using LLMs for coding?
203 points · 202 comments
Claude-real-video - any LLM can watch a video
github.com · 166 points · 60 comments
Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
twitter.com · 977 points · 690 comments