Qwen

Feeds to Scour
SubscribedAll
Scoured 175 posts in 7.4 ms

Aspen: Own your intelligence

 🔵Gemini  Content type: Discussion  Content type: Tutorial

Geekom's 'high-performance' AI mini PC gets a massive discount with our exclusive money-off code — ahead of Prime Day, not even Amazon can beat it on price

 🔵Gemini
techradar.com
·

Qwen 3.6 27B AutoRound GGUF, need your feedback

 🟢OpenAI

Running LLM Inference on Kubernetes: What It Actually Takes

 🤖AI  Content type: Blog
fairwinds.com·

Making Locality-aware GEMM Compatible with Page-Granularity Placement on Chiplet GPUs

 💬LLMs  Content type: Academic
arxiv.org·

What's in the Box? A Field Guide to AI Models

 🤖AI  Content type: Blog
iankduncan.com·

martidu4/honey-ai: 🍯 All-in-one AI honeypot powered by local LLMs. SSH, HTTP, FTP, Telnet, SMTP, MySQL, Redis, Git, VNC, RDP — with canary tokens, tarpits, GZIP bombs, and threat intel reporting.

 🟢OpenAI  Content type: Code
github.com··Hacker News

Ask HN: Is it feasible to run a model on device for complete privacy?

 💬LLMs  Content type: Discussion

Comparative Analysis of Inference-Time Defense Methods for Multimodal Large Language Models

 💬LLMs  Content type: Academic
arxiv.org·

Making FlashAttention-4 faster for inference

 🟢OpenAI  Content type: Blog
modal.com··Hacker News

How to Make Your SMALL Local AI Models 10X SMARTER

 🕵️AI Agents  Content type: Video
youtube.com·

I built a portfolio website using Claude Design's open-source alternative, and it gave Claude a real run for its money

 🟢OpenAI
xda-developers.com·

BeeLlama.cpp DFlash on Strix Halo: 2.7x Gemma 31B, But MTP Is Still Faster

 🟢OpenAI
sleepingrobots.com·

linzhiqiu/t2v_metrics: Evaluating text-to-image/video/3D models with VQAScore

 🔵Gemini  Content type: Code
github.com··Hacker News

Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs

 💬LLMs
lesswrong.com·

The great AI Irony: China cracks down on Western models while US companies flock to DeepSeek

 🤍Claude  Content type: News
techradar.com
·

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

 🕵️AI Agents  Content type: Academic
arxiv.org·

Dnotitia Releases DNA 3.0, an Enterprise-Ready AI Language Model Family - HPCwire

 🤖AI
hpcwire.com·

Progress: real and Potemkin

 🧠AGI  Content type: Blog

everest-an/M1: AwareLiquid — MT-LNN with cloud-augmented memory, deliberation router, capsule v2, and Φ̂ reasoning trace. Improved successor to O1 (clean MT-LNN prototype).

 🟢OpenAI  Content type: Code
github.com··Hacker News
Sign up or log in to see more results

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