Context Windows

Feeds to Scour
SubscribedAll
Scoured 121 posts in 10.6 ms

We Should Take Text Optimization More Seriously

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

markusheimerl/gpt: A generative pretrained transformer implementation

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

Claude Fable 5 Free Through June 22 on Pro, Max, Team, and Enterprise Plans

 🎭Anthropic Claude  Content type: News
claude5.ai··Hacker News

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

 🤝AI Agents

Introducing the Third Generation of Apple’s Foundation Models

 💬LLMs

DeepSeek Made AI Cheap. Now It Needs Billions to Keep It Cheap.

 🤝AI Agents  Content type: News  Content type: Blog

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

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

Claude Fable 5 and Mythos 5 pricing: Anthropic's new $10/$50 top tier

 🎭Anthropic Claude

See, Act, Correct: three levers for working with a code agent

 🤖Agent Architecture  Content type: Blog

harshuljain13/llm-inference-at-scale: A Practitioner handbook for production llm serving.

 🤖LLM  Content type: Code
github.com··Hacker News

NVIDIA Nemotron 3 Ultra Powers Faster, More Efficient Reasoning for Long-Running Agents

 🤖Agent Architecture  Content type: Blog

Do Transformers Need Three Projections? Systematic Study of QKV Variants

 📱Edge AI  Content type: Academic
arxiv.org··Hacker News

defai-digital/ax-engine: Apple Silicon LLM runtime supporting Gemma 4 and Qwen 3.6 MTP modes

 🤖LLM  Content type: Code
github.com··Hacker News

Magenta RealTime 2: Open and Local Live Music Models

 🎤Voice Interfaces

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency

 🦙Ollama  Content type: News  Content type: Blog
blog.google··Hacker News

ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

 🤖LLM  Content type: Code
github.com··Hacker News

Maybe Coding Agents Don't Need a Bigger Memory. Maybe They Need Continuity.

 🏛️Memory Palaces  Content type: News  Content type: Blog

How LLMs work | Practical Leaders

 🤖LLM

Bad MCP design cost your Agent 5× more tokens

 🔌MCP  Content type: Discussion

Replace your CI with a merge queue

 💬LLMs  Content type: Blog
blog.exe.dev··Hacker News

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