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.
898 stories archived · Page 27 of 30
RSS feed for LLMA production-grade OCR pipeline on Kubernetes with vLLM and Rust
github.com · 7 points · 0 comments
How are you getting decent front end interface results out of LLMs?
2 points · 1 comments
Why I joined Blacksmith to work on storage again
blacksmith.sh · 16 points · 2 comments
Extension that shows complaints and more on NYC apartment listings
streetleaky.com · 3 points · 1 comments
My security camera shipped a GitHub admin token in its login page
hhh.hn · 645 points · 242 comments
LLM Proxy - Python with SSE stream aggregation and timeout prevention
github.com · 2 points · 0 comments
Hetzner is working on LLM Inference
sliplane.io · 155 points · 86 comments
RTK and Claude Code Token Savings: A Closer Look
blog.jetbrains.com · 6 points · 0 comments
filtersql – a dependency-free JSON-to-SQL compiler for LLMs and WebAPIs
github.com · 3 points · 1 comments
Naming a pattern in AI-generated code: Modular Mirage
2 points · 0 comments
Computer science enrollment fell for the first time in 20 years
businessinsider.com · 10 points · 3 comments
A Pragmatic Approach to LLMs
gracefulliberty.com · 8 points · 0 comments
Gigatoken-rb – A Ruby port of gigatoken that's 1.6x faster
github.com · 4 points · 0 comments
Coypa is a fun way to manage your clipboard
github.com · 3 points · 1 comments
Letterpaths: Or how LLMs can be good even when they're bad
robinlinacre.com · 6 points · 1 comments
Turo – An Aggressive Token-Saving Proxy for CLI AI Agents
github.com · 4 points · 2 comments
AI bet goes awry: Oracle fires 21,000 employees
jpost.com · 16 points · 3 comments
Connecting my dumb garage and car's homelink buttons to Home Assistant
dsauerbrun.com · 11 points · 0 comments
Ask: Why does everything Microsoft create lately feel fragile and half-baked?
9 points · 11 comments
AI Coding Will Prevent Expertise
larsfaye.com · 5 points · 0 comments
Grounded-forge: RAG with summaries and task views precomputed at ingest
github.com · 2 points · 0 comments
Notebooker.ai – NotebookLM alternative, your own models, keys, storage
notebooker.ai · 3 points · 0 comments
Flow Matching model inference in C
github.com · 5 points · 2 comments
A primer for non-coders to design software via structured AI dialogue
github.com · 6 points · 1 comments
WatchMachineGo – A visualizer to show hardware performing LLM inference
watchmachinego.com · 2 points · 1 comments
Whetuu – a zero-config cross-shell prompt written in Zig
yamafaktory.github.io · 50 points · 38 comments
Avoiding the Memory Wall by computing LLM inference directly inside RAM
3 points · 0 comments
What's AI's go-to, public or private healthcare?
modelbias.ai · 8 points · 3 comments
Petals: Run LLMs at home, BitTorrent-style
petals.dev · 137 points · 38 comments
Protecting our FLOSS commons from LLMs
blog.codeberg.org · 201 points · 147 comments