Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
AI
馃 AI
Broad
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
344
posts in
12.5
ms
SLUUG Talk: Demystifying
Large
Language
Models
on Linux
聽
馃弸
Gym
聽
Content type:
Code
github.com
路
3d
3 days ago
路
DEV
Actions for SLUUG Talk: Demystifying Large Language Models on Linux
The Neutral Mask: How
RLHF
Provides Shallow Alignment while Leaving Partisan Structure Intact in a
Large
Language
Model
聽
馃弸
Gym
聽
Content type:
Academic
arxiv.org
路
1d
1 day ago
Actions for The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model
Shrinking a
Neural
Network
Often Makes It Smarter
聽
馃弸
Gym
siliconopera.com
路
14h
14 hours ago
Actions for Shrinking a Neural Network Often Makes It Smarter
Fine
tuning
classification in Elixir
聽
馃弸
Gym
elixirstatus.com
路
2d
2 days ago
Actions for Fine tuning classification in Elixir
Sequent: scale and automation for higher confidence in alignment
聽
馃
Agent
lesswrong.com
路
8h
8 hours ago
Actions for Sequent: scale and automation for higher confidence in alignment
Using local LLMs for agentic coding
聽
馃
Agent
聽
Content type:
Blog
blog.alexewerlof.com
路
6d
6 days ago
Actions for Using local LLMs for agentic coding
Apple WWDC On-Device
AI
Deep
Dive - Google Docs
聽
馃弸
Gym
gist.is
路
2h
2 hours ago
路
Hacker News
Actions for Apple WWDC On-Device AI Deep Dive - Google Docs
The Rise of Agentic
AI
: What Every Engineer Should
Learn
聽
馃
Agent
聽
Content type:
Blog
medium.com
路
2d
2 days ago
Actions for The Rise of Agentic AI: What Every Engineer Should Learn
Google鈥檚 DiffusionGemma is 4x faster than its other Gemma
models
聽
馃弸
Gym
thenewstack.io
路
7h
7 hours ago
Actions for Google鈥檚 DiffusionGemma is 4x faster than its other Gemma models
AMD's Lemonade SDK For Local
AI
Adds NVIDIA CUDA Support
聽
馃弸
Gym
phoronix.com
路
8h
8 hours ago
Actions for AMD's Lemonade SDK For Local AI Adds NVIDIA CUDA Support
New comment by Revanthkodati in "Ask HN: Who wants to be hired? (June 2026)"
聽
馃弸
Gym
drive.google.com
路
2d
2 days ago
路
Hacker News
Actions for New comment by Revanthkodati in "Ask HN: Who wants to be hired? (June 2026)"
Evaluating and developing
machine
learning
models
: 盲N introduction (gpn24)
聽
馃
Agent
cdn.media.ccc.de
路
6d
6 days ago
Actions for Evaluating and developing machine learning models: 盲N introduction (gpn24)
Siri
AI
at WWDC 2026
聽
馃弸
Gym
simonwillison.net
路
2d
2 days ago
路
Hacker News
Actions for Siri AI at WWDC 2026
NVIDIA Accelerates Google
DeepMind
鈥檚 DiffusionGemma for Local
AI
聽
馃弸
Gym
聽
Content type:
Blog
blogs.nvidia.com
路
8h
8 hours ago
Actions for NVIDIA Accelerates Google DeepMind鈥檚 DiffusionGemma for Local AI
Using Scikit-LLM with Open-Source LLMs
聽
馃弸
Gym
machinelearningmastery.com
路
6d
6 days ago
Actions for Using Scikit-LLM with Open-Source LLMs
Stop
hand-tuning
kernels: How Neuron Agentic Development accelerates AWS Trainium optimizations
聽
馃
Agent
聽
Content type:
Blog
aws.amazon.com
路
9h
9 hours ago
Actions for Stop hand-tuning kernels: How Neuron Agentic Development accelerates AWS Trainium optimizations
Your
AI
agent reads the
fine
print: building a
RAG
pipeline over EU regulations with Elasticsearch and OGX
聽
馃
Agent
聽
Content type:
Blog
elastic.co
路
1d
1 day ago
Actions for Your AI agent reads the fine print: building a RAG pipeline over EU regulations with Elasticsearch and OGX
local llm on laptop 780M GPU using
llama
+ gemma 4 qat
聽
馃弸
Gym
聽
Content type:
Blog
alper.bearblog.dev
路
4d
4 days ago
Actions for local llm on laptop 780M GPU using llama + gemma 4 qat
Location: Lubbock, TX, USA Remote: Yes (Remote-friendly, US-based) Technologies:...
聽
馃
Agent
聽
Content type:
Discussion
news.ycombinator.com
路
9h
9 hours ago
路
Hacker News
Actions for Location: Lubbock, TX, USA Remote: Yes (Remote-friendly, US-based) Technologies:...
Train
Models
Faster with JAX and MaxText Using NVFP4 on NVIDIA Blackwell
聽
馃弸
Gym
聽
Content type:
News
聽
Content type:
Blog
developer.nvidia.com
路
2d
2 days ago
Actions for Train Models Faster with JAX and MaxText Using NVFP4 on NVIDIA Blackwell
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
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
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help