LLMs

large language models, GPT, Claude, inference, fine-tuning

Feeds to Scour
SubscribedAll
Scoured 293 posts in 17.6 ms

The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

What Are Tokens in LLMs?

 Formal Verification  Content type: Blog

Timing Trick Cuts Energy Used in LLM Training by Up to 14 Percent

 🧠Neural Networks  Content type: News
spectrum.ieee.org
··Hacker News

Report: GKE Inference Gateway delivers up to 92% faster AI responses

 ⚙️AI Engineering  Content type: Blog

Massive AI Storage Demand Creates a New Memory Wall

 ⚙️AI Engineering  Content type: News
eetimes.com·

SLUUG Talk: Demystifying Large Language Models on Linux

 🧠Neural Networks  Content type: Code
github.com··DEV

Why LLMs (still) lack taste

 🎮Reinforcement Learning

The biggest local LLM on your machine is useless if it can't call a single tool, no matter how many parameters it has

 🤖AI Agents
xda-developers.com·

The Bill Arrives: How to Manage Agentic AI Costs at Scale

 🤖AI Agents  Content type: Blog
cockroachlabs.com·

Comprehensive evaluation of LLM capabilities for interpretation and analysis of genome-scale metabolic models in metabolic engineering

 ⚙️AI Engineering  Content type: Academic
biorxiv.org·

Using Scikit-LLM with Open-Source LLMs

 🔧MLOps

Alignment Defends LLMs from Property Inference Attacks

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

LangChain Explained: Understanding Models, Prompts, Chains, Memory, Indexes, and Agents

 ⚙️AI Engineering  Content type: Blog
towardsai.net·

A Plea to the Labs: Let the Models Diagnose.

 🔧MLOps  Content type: Blog

Claude vs GPT-4: Which AI API Is Better for Developers? (2026)

 🛡️Anthropic
kalyna.pro··DEV

Train Models Faster with JAX and MaxText Using NVFP4 on NVIDIA Blackwell

 🤝AI-Assisted Coding  Content type: News  Content type: Blog
developer.nvidia.com·

OpenCV 5 release - New DNN engine with enhanced ONNX and LLM/VLM support, Intel, Arm, and RISC-V hardware optimizations - CNX Software

 🧠Neural Networks  Content type: News
cnx-software.com·

tetherto/qvac: QVAC - Local AI SDK and libraries for building private, cross-platform, peer-to-peer AI applications. Run LLMs, speech-to-text, translation, and more locally on Linux, macOS, Windows, Android, and iOS.

 ⚙️AI Engineering  Content type: Code
github.com·

VArify: A Visual Analytics System for Verifying Knowledge Enhanced Large Language Model Responses in Food Science

 🕸️Knowledge Graphs  Content type: Academic
arxiv.org·

Modernizing attendance ticketing in SAS Viya using SAS Agentic AI Accelerator

 ⚙️AI Engineering  Content type: Blog
blogs.sas.com·

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