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
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
491
posts in
9.0
ms
Prompt
Engineering
Is Dead. Process
Engineering
Is the New AI Skill.
💻
computer science
Content type:
Blog
medium.com
·
10h
10 hours ago
Actions for Prompt Engineering Is Dead. Process Engineering Is the New AI Skill.
AIs like ChatGPT fall apart in classic 'Stroop' psychological test — and that could stand in the way of achieving artificial
general
intelligence
🔬
science
techradar.com
·
5d
5 days ago
Actions for AIs like ChatGPT fall apart in classic 'Stroop' psychological test — and that could stand in the way of achieving artificial general intelligence
I added this open-source tool to my local AI stack, and my local
LLM
finally
has persistent memory
🏠
selfhosting
xda-developers.com
·
1d
1 day ago
Actions for I added this open-source tool to my local AI stack, and my local LLM finally has persistent memory
Indirect
Prompt
Injection remains a fundamental security challenge for AI
🏗️
Systems Design
Content type:
Blog
brave.com
·
2d
2 days ago
Actions for Indirect Prompt Injection remains a fundamental security challenge for AI
MLPerf and the rise of latency-aware
LLM
benchmarking
🏗️
Systems Design
edn.com
·
5d
5 days ago
Actions for MLPerf and the rise of latency-aware LLM benchmarking
Dep-LLM
:
Training-Free
Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable
LLM
Reasoning
🔬
science
Content type:
Academic
arxiv.org
·
14h
14 hours ago
Actions for Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning
Meet Hades: The malware that lies to AI security agents
🏠
selfhosting
Content type:
News
infoworld.com
·
1d
1 day ago
·
Hacker News
Actions for Meet Hades: The malware that lies to AI security agents
Guardian Angels:
LLM
Personalization for Productivity and Security
🏠
selfhosting
gwern.net
·
3d
3 days ago
·
Hacker News
Actions for Guardian Angels: LLM Personalization for Productivity and Security
Evaluate your Amazon Nova Sonic voice agent at scale, no microphone required
🏠
selfhosting
Content type:
Blog
aws.amazon.com
·
2d
2 days ago
Actions for Evaluate your Amazon Nova Sonic voice agent at scale, no microphone required
Why Shrinking an AI
Model
Often Makes It More Useful
🏗️
Systems Design
siliconopera.com
·
3d
3 days ago
Actions for Why Shrinking an AI Model Often Makes It More Useful
KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K
context
on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe
Flash-Attention
for
llama.cpp
, fully measured on real hardware.
🏗️
Systems Design
Content type:
Code
github.com
·
2h
2 hours ago
·
Hacker News
Actions for KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.
SIGMOD 2026 Recap
🏗️
Systems Design
Content type:
Blog
emptysqua.re
·
1d
1 day ago
Actions for SIGMOD 2026 Recap
Adrarsh Divakaran: Building AI Agents in Python
🏗️
Systems Design
Content type:
Blog
blog.adarshd.dev
·
6d
6 days ago
Actions for Adrarsh Divakaran: Building AI Agents in Python
A wild idea: Abstract reality using ontology
🏗️
Systems Design
Content type:
Discussion
news.ycombinator.com
·
4d
4 days ago
·
Hacker News
Actions for A wild idea: Abstract reality using ontology
Do nothing at work 💼, performative UI 🎨, routing token spend 👣
🏗️
Systems Design
tldr.tech
·
1d
1 day ago
Actions for Do nothing at work 💼, performative UI 🎨, routing token spend 👣
REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of
LLMs
🏗️
Systems Design
Content type:
Academic
arxiv.org
·
14h
14 hours ago
Actions for REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs
Researchers
trained
an open source AI search agent, Harness-1, that outperforms
GPT-5.4
on recalling relevant information
🏠
selfhosting
venturebeat.com
·
1d
1 day ago
·
Hacker News
Actions for Researchers trained an open source AI search agent, Harness-1, that outperforms GPT-5.4 on recalling relevant information
Can activation verbalizers surface an internal
chain
of
thought
?
🔬
science
lesswrong.com
·
3d
3 days ago
Actions for Can activation verbalizers surface an internal chain of thought?
AI Glossary
🏠
selfhosting
Content type:
Blog
0xdf.gitlab.io
·
6d
6 days ago
Actions for AI Glossary
Show HN: Lore –
LLM
proxy for coding agent
context
and memory management
🏗️
Systems Design
withlore.ai
·
1d
1 day ago
·
Hacker News
Actions for Show HN: Lore – LLM proxy for coding agent context and memory management
Sign up or log in to see more results
Sign Up
Login
« 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