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.
888 stories archived · Page 1 of 30
RSS feed for LLMRedthread – autonomous LLM pentesting with proof-of-concept exploits
millenniums.ai · 2 points · 0 comments
Prompting Claude Opus 5.5
platform.claude.com · 36 points · 15 comments
"The refrigerator is dead": Samsung's AI fridges shut down after update
notebookcheck.net · 8 points · 2 comments
Cartopolis, interactive globe-sized 3D world
code.garage44.eu · 13 points · 3 comments
Squint – Drag a box on your screen and ask AI about it
heysquint.com · 3 points · 0 comments
Fragment of oldest known peace treaty found in Turkey
livescience.com · 15 points · 11 comments
How are you getting inference for personal projects?
2 points · 3 comments
"As a Language Model": Chat Template Switches LLM Self-Referential Voice
arxiv.org · 65 points · 64 comments
Claude Deleted 48k Files
web.archive.org · 4 points · 0 comments
42x faster prompt lookup drafting in llama.cpp
jadidbourbaki.github.io · 7 points · 12 comments
Font where each token is equal-width
twitter.com · 4 points · 1 comments
Understanding the Impact of LLM Watermarking on AI Agent Behavior
lasso.security · 19 points · 71 comments
How to keep enjoying programming in a world of LLMs
discourse.haskell.org · 17 points · 331 comments
A single function Jev-like wrapper for LLMs, including vision models
allanrbo.blogspot.com · 44 points · 44 comments
Generate fonts where every LLM token is the same width
ampdot.mesh.host · 3 points · 22 comments
Advice to a Beginning Graduate Student (2001)
cs.cmu.edu · 23 points · 21 comments
Towards GPU Type Inference
winwang.blog · 7 points · 0 comments
Xtriever – offline RAG retrieval on a phone
github.com · 2 points · 0 comments
Ctxfw – In-memory AST pruner and token firewall for Cursor and Claude
github.com · 2 points · 0 comments
How do you use LLMs to secure your code and services?
3 points · 1 comments
Running local LLMs on your Mac: what fits, what's free, and what's overkill
typetab.app · 4 points · 0 comments
I stopped letting LLMs do arithmetic
medium.com · 7 points · 1 comments
OpenAI and Microsoft Admits LLMs Are Destroying the Web and Built on Theft
404media.co · 8 points · 1 comments
Paul Graham on LLMs 'Thinking'
twitter.com · 12 points · 27 comments
Fine-tuned 110M encoder beat 7B LLMs and hybrid search for NIST mapping
github.com · 2 points · 0 comments
Using LLMs to trace alchemical knowledge and decode 17th century letters
resobscura.substack.com · 32 points · 43 comments
Best LLM for every budget, updated daily
bestmodelforyourbudget.terrydjony.com · 3 points · 112 comments
Jev Is Not a Language Model, but It Breaks Like One
blog.checkpoint.com · 30 points · 6 comments
What Is RLCD? The Secret Behind Jev
di-zhang-llm.github.io · 8 points · 8 comments
Can open-source prompt-injection detectors catch realistic AI agent attacks?
github.com · 6 points · 3 comments