Hugging Face

Feeds to Scour
SubscribedAll
Scoured 189 posts in 6.8 ms

What Does Abliteration Actually Cost?

 🧠LLM
lesswrong.com·
Less-relevant results

Claude Fable 5 and new AI safety fables

 🎯Fine-tuning  Content type: News

Quality Is Not a Safety Proxy Under Quantization

 🎯Fine-tuning  Content type: Academic
arxiv.org·

Stable-Worldmodel: A High Performance Platform for Reproducible World Model Research

 🖼️Multimodal AI  Content type: Blog
lancedb.com·

Google fills out the middle with the Gemma 4 12B

 🤖AI Agents
jonpeddie.com·

NVIDIA releases Nemotron 3 Ultra, claiming five times the speed and 30 percent lower costs than prior modelsThe model delivers 300 tokens per second on benchmar...

 🎯Fine-tuning
digg.com·

Engineers who helped build Salesforce’s Agentforce raised $5.1M to build its opposite

 🤖AI Agents  Content type: News
thenextweb.com·

Tejas-TA/predikit: The missing bridge between your ML models and your AI agents.

 Machine Learning  Content type: Code
github.com··Hacker News

Can Voice Agents Handle Bilingual Customers? Benchmarking Frontier ASR on Code-Switched Speech

 🧠LLM  Content type: Blog
huggingface.co·

Build a Medical Report Analyzer on Dedicated Inference with Python

 🧠LLM
digitalocean.com·

Running LLM Inference on Kubernetes: What It Actually Takes

 🧠LLM  Content type: Blog
fairwinds.com·

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

 🤖AI Agents  Content type: Blog
cohere.com··Hacker News

Google's new open model DiffusionGemma generates text from noise instead of word by word

 🧠LLM
the-decoder.com
·

BioMedGraphica: An All-in-One Platform for Joint Textual Biomedical Prior Knowledge and Numeric Graph Generation

 📚RAG
academic.oup.com
·

SafeRun: Enabling Determinism in LLM Planning for Running

 ⚙️MLOps  Content type: Academic
arxiv.org·

Three sleep intervals for three APIs: Steam 250ms, GitHub 100ms, HuggingFace none

 🎯Fine-tuning  Content type: Reference
docs.github.com··DEV

Can You Hide From a Natural Language Autoencoder?

 🎯Fine-tuning  Content type: Blog
yogesh.bearblog.dev·

Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search

 🧠LLM

[AINews] FrontierCode: Benchmarking for Code Quality over Slop

 🔗LangChain  Content type: News
latent.space
·

AI Chart Understanding Breakthrough: MIT-IBM Dataset Lets Small Models Beat GPT-4o

 🖼️Multimodal AI
techtimes.com·
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