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
LLMs
🧠 LLMs
large language models, foundation models, transformer, GPT
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
1034
posts in
6.5
ms
Acoda: Adversarial Code Obfuscation for Defending against
LLM-based
Analysis
⚙️
MLOps
Content type:
Academic
arxiv.org
·
20h
20 hours ago
Actions for Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis
google/gemma-4-12B-it-qat-q4
_0-gguf
🤖
AI Agents
huggingface.co
·
6d
6 days ago
Actions for google/gemma-4-12B-it-qat-q4_0-gguf
defai-digital/ax-engine: Apple Silicon
LLM
runtime supporting
Gemma
4 and
Qwen
3.6 MTP modes
🤖
AI Agents
Content type:
Code
github.com
·
2d
2 days ago
·
Hacker News
Actions for defai-digital/ax-engine: Apple Silicon LLM runtime supporting Gemma 4 and Qwen 3.6 MTP modes
Orchestrate your
LLM
pipeline. Locally
⚙️
MLOps
llmforge.app
·
8h
8 hours ago
·
Hacker News
Actions for Orchestrate your LLM pipeline. Locally
GPT
fdisk Tutorial
✍️
Prompt Engineering
rodsbooks.com
·
1d
1 day ago
Actions for GPT fdisk Tutorial
How ChatGPT Actually Works (Beginner Friendly)
🔌
MCP
Content type:
Blog
medium.com
·
49m
49 minutes ago
Actions for How ChatGPT Actually Works (Beginner Friendly)
Show HN: In-browser real
LLM
token counter and cost estimation
✍️
Prompt Engineering
holaclaw.ai
·
9h
9 hours ago
·
Hacker News
Actions for Show HN: In-browser real LLM token counter and cost estimation
Florian Brand, Prime Intellect research engineer, adopts
Gemma
4 E4B 6-bit quantized as his primary local Mac
LLM
✍️
Prompt Engineering
Content type:
News
digg.com
·
4d
4 days ago
·
Hacker News
Actions for Florian Brand, Prime Intellect research engineer, adopts Gemma 4 E4B 6-bit quantized as his primary local Mac LLM
Context
windows
in AI: why every token is a budget decision
✍️
Prompt Engineering
Content type:
Blog
redis.io
·
1d
1 day ago
Actions for Context windows in AI: why every token is a budget decision
How
LLMs
are Actually Trained
📊
OOD Detection
Content type:
News
Content type:
Blog
blog.algomaster.io
·
19h
19 hours ago
Actions for How LLMs are Actually Trained
DiffusionGemma: Discrete diffusion in a
large
language
model
🏷️
Label Noise
idlemachines.co.uk
·
2h
2 hours ago
·
Hacker News
Actions for DiffusionGemma: Discrete diffusion in a large language model
Google fills out the middle with the
Gemma
4 12B
⚙️
MLOps
jonpeddie.com
·
2d
2 days ago
Actions for Google fills out the middle with the Gemma 4 12B
The latest
Gemma
4
models
use a training trick to slash their on-device memory footprint
⚙️
MLOps
androidauthority.com
·
6d
6 days ago
Actions for The latest Gemma 4 models use a training trick to slash their on-device memory footprint
Why Your
LLM
Gets Dumber With More
Context
✍️
Prompt Engineering
siliconopera.com
·
10h
10 hours ago
Actions for Why Your LLM Gets Dumber With More Context
My Notes on the Progression from
Context
to Prompt to Harness engineering in making
GPT
LLMs
Useful: (TUESDAY) MAMLMs
🤖
AI Agents
Content type:
News
Content type:
Blog
braddelong.substack.com
·
2d
2 days ago
·
Substack
Actions for My Notes on the Progression from Context to Prompt to Harness engineering in making GPT LLMs Useful: (TUESDAY) MAMLMs
Failing to Ragebait the New
Gemma
✍️
Prompt Engineering
lesswrong.com
·
6h
6 hours ago
Actions for Failing to Ragebait the New Gemma
Unsloth
Gemma
4 QAT
⚙️
MLOps
unsloth.ai
·
6d
6 days ago
Actions for Unsloth Gemma 4 QAT
Two old GPUs I salvaged are doing more AI work than a brand new $2000 card, and I won't be upgrading anytime soon
⚙️
MLOps
xda-developers.com
·
8h
8 hours ago
Actions for Two old GPUs I salvaged are doing more AI work than a brand new $2000 card, and I won't be upgrading anytime soon
lightmetal: GPU
LLM
Inference From a Single Java 25 JAR
⚙️
MLOps
Content type:
Blog
adambien.blog
·
2d
2 days ago
Actions for lightmetal: GPU LLM Inference From a Single Java 25 JAR
Prompt Caching Explained: The AI Concept That Can Save Millions of Tokens
✍️
Prompt Engineering
Content type:
Blog
sweta-nit.medium.com
·
16h
16 hours ago
Actions for Prompt Caching Explained: The AI Concept That Can Save Millions of Tokens
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