LLM

Feeds to Scour
SubscribedAll
Scoured 472 posts in 16.6 ms

Best explanations of how LLMs work

 📊Embeddings  Content type: Blog

sudomichael/agentgraphed: Local-first analytics dashboard for AI coding sessions. See what you built with Claude Code & Codex CLI.

 🎭Anthropic Claude  Content type: Code
github.com··Hacker News

What Is an Agent?

 🤖Agent Architecture  Content type: News  Content type: Blog

How we fight GPU scarcity without compromise

 💬LLMs  Content type: Blog
equixly.com··Hacker News

Show HN: Agent-pd – A zero-token audit log to catch rogue Claude Code subagents

 🎭Anthropic Claude  Content type: Code
github.com··Hacker News

LLM AI Chatbots are letting me down every single day

 📝NLP

Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

 💬LLMs  Content type: Academic
arxiv.org··Hacker News

orion-arm-ai/tinytasktree: A tiny async task-tree orchestrator library for Python, behavior-tree inspired and LLM-ready.

 💬LLMs  Content type: Code
github.com··Hacker News

Show HN: Run Llama.cpp In-Process from Java with Project Panama FFM

 🦙Ollama

How to design pricing for AI APIs and LLM-powered products

 🎭Anthropic Claude  Content type: Blog
solvimon.com··Hacker News

I'm tired of LLM skill slop, so I built mine with regression tests

 🎭Anthropic Claude  Content type: Discussion

Matrix – An installable Python CLI package for cross-device session jumping

 🦙Ollama  Content type: Code
github.com··Hacker News

Did Claude Increase Bugs in Rsync?

 Zed

LLM Research Papers: The 2026 List (January to May)

 🪟Context Windows  Content type: News

CodegenBench: Can LLMs Write Efficient Code Across Architectures?

 💬LLMs  Content type: Academic
arxiv.org··Hacker News

Guardian Angels: LLM Personalization for Productivity and Security

 💬LLMs
gwern.net··Hacker News

Don't dethrone consciousness

 🤔Philosophy  Content type: News

StereoTales: Multilingual Open-Ended Stereotype Discovery in LLMs

 📝NLP  Content type: Blog

john-rocky/apple-silicon-llm-bench: Neutral, reproducible benchmark for local LLMs on Apple Silicon (Mac · iPhone · iPad) — MLX, llama.cpp, CoreML, Apple Foundation Models

 📱Edge AI  Content type: Code
github.com··Hacker News

If Claude Fable stops helping you, you'll never know

 🎭Anthropic Claude  Content type: Blog

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help