Open Source AI

Feeds to Scour
SubscribedAll
Scoured 598 posts in 9.3 ms

Hugging Face Transformers RCE flaw enables stealthy compromise via AI model configs

 🏆SOTA Models
csoonline.com·

"North Mini Code"; open weights, 30B param, Canadian coding model

 👨‍💻Coding Agents  Content type: Blog
cohere.com··Hacker News

Build a Medical Report Analyzer on Dedicated Inference with Python

 🧠LLMs
digitalocean.com·

WWDC 2026: Foundation Models (& Anarlog)

 🐳Containers
skushagra.com·

Open Source when it comes to AI needs to meet something....

 🏆SOTA Models
timothychambers.net·

Xiaomi MiMo-V2.5-Pro Just Hit 1,000 Tokens Per Second!

 Inference
gizchina.com·

Malicious Hugging Face Models Could Trigger Remote Code Execution

 📦Sandboxing
techrepublic.com·

libertywing/FlashMemory-Deepseek-V4: FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.

 Inference  Content type: Code
github.com·

Google Shrank Gemma 4 by 72% and Unsloth Fixed the 4-Bit Bug Nobody Else Caught on One 4090, and 4-Bit Shouldn’t Be This Good

 Inference  Content type: Blog
towardsai.net·

Large companies can add a local LLM filter layer to considerably reducing their AI costs

 Inference

Building & Benchmarking: LLMs on a 16GB Jetson Orin NX for Hermes Agent

 Inference  Content type: Blog
dnhkng.github.io·

DeskDash - a free Windows tool to easily manage your GGUF files

 📐Context Engineering

Automatic Extraction of Structured Information from Brain MRI Reports Using an Open-Weight Large Language Model

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

Self-hosted remote access for Ollama without complicated setup

 🎛️Fine-tuning

Ideogram 4.0 launches with 2K resolution and top open-weight ranking

 🏆SOTA Models
alternativeto.net·

Local LLMs, Buy a GPU, and the Case for Cognitive Security

 🧠LLMs

Can You Code With 1-Bit AI Model?

 👨‍💻Coding Agents  Content type: Video
youtube.com·

iChristGit/comfyui-llamacpp-ideogram: ComfyUI Prompt enhancer for ideogram4 powered by llama cpp

 ✍️Prompt Engineering  Content type: Code

Hugging Face Transformers flaw enables RCE via malicious model configs

 👨‍💻Coding Agents
4sysops.com·

Multimedia Building Blocks

 👨‍💻Coding Agents  Content type: Blog
huggingface.co·
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