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 9 of 30
RSS feed for LLMRedactle LLM Leaderboard
redactle.net · 5 points · 1 comments
Headed for the Exit: The Great Engineering Leader Career Break
newsletter.pragmaticengineer.com · 3 points · 0 comments
Codeknow – Architecture health scores for any codebase, no LLM needed
github.com · 4 points · 2 comments
What Makes LLM Tokenization Slow?
healeycodes.com · 3 points · 0 comments
Mushroom hunting with LLMs: what can go wrong?
quesma.com · 45 points · 76 comments
Sleeper Agents in Robot Dogs and Kinetic Prompt Injections
eito.substack.com · 3 points · 0 comments
OpenAI's agents exploited a patched Linux bug in Hugging Face incident
zdnet.com · 7 points · 0 comments
Saving money on Google Photos with Immich: Your own personal photo storage
markpitblado.me · 114 points · 137 comments
Offshoots of cancelled TrueNAS Core upgrade to FreeBSD 15
theregister.com · 3 points · 0 comments
WebLLM: high-performance in-browser LLM inference engine
github.com · 6 points · 25 comments
LLMs: Intelligence vs. Cost
openteams.com · 96 points · 42 comments
My local model setup on an M4 Pro Mac Mini
3 points · 0 comments
MC/DC coverage so coding agents could work overnight
supercov.com · 2 points · 0 comments
LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes
arxiv.org · 15 points · 14 comments
US may ask parents to prove citizenship to get passports for their children
reuters.com · 9 points · 6 comments
LLMs and Self-Referentiality
scottaaronson.blog · 55 points · 94 comments
The efficient frontier of LLM inference
baseten.co · 47 points · 46 comments
Mcptunnels – ngrok for MCP with basic OAuth
terragohan.github.io · 12 points · 4 comments
Claude and ChatGPT need a datacenter. This runs on my phone
llmobi.pages.dev · 2 points · 7 comments
Semantic Overlays – an NX bit for LLM prompt injection (live demo)
semantic-overlays.vercel.app · 4 points · 0 comments
Openheim – a multi-provider LLM agent runtime, written in Rust
openheim.io · 3 points · 0 comments
We could save petabytes of cache storage with Zstandard and Pingora
blog.cloudflare.com · 9 points · 62 comments
OSS, K8s-native AI platform for distributed multi-model inference
github.com · 4 points · 0 comments
Stanisław Lem foretold the current LLM mania in 1964
nibblestew.blogspot.com · 28 points · 0 comments
Why Syracuse Can't Attract the Students It Needs to Pay the Bills
wsj.com · 7 points · 0 comments
A frozen LLM with external memory found a novel 26 circle packing structure
blankline.org · 3 points · 0 comments
Creating backup storage sucks
smarmelling.com · 50 points · 67 comments
Are Prompt Injections "Malware"?
2 points · 11 comments
The EU has begun enforcing the AI Act: first RFIs to model providers
tokenstead.ai · 42 points · 101 comments
I asked LLMs to choose between popular developer tools
github.com · 4 points · 0 comments