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
LLM Alignment
🧭 LLM Alignment
AI alignment, RLHF, model behavior, interpretability
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
156
posts in
5.7
ms
Mathematical proof reveals why fixed
AI
guardrails can never block every
jailbreak
🛡️
AI Safety
techxplore.com
·
10h
10 hours ago
Actions for Mathematical proof reveals why fixed AI guardrails can never block every jailbreak
local
AI
agents for Cursor with pre-tuned marketplace/commu
🎭
AI Simulators
locaible.com
·
12h
12 hours ago
·
Hacker News
Actions for local AI agents for Cursor with pre-tuned marketplace/commu
Why LLMs (still) lack taste
🎭
AI Simulators
beyondtheprior.com
·
2d
2 days ago
·
Hacker News
Actions for Why LLMs (still) lack taste
Controversial smut as an
AI
alignment
issue
🛡️
AI Safety
Content type:
News
Content type:
Blog
thingofthings.substack.com
·
5d
5 days ago
·
Substack
Actions for Controversial smut as an AI alignment issue
Posting for authoring
📝
Long-form Essays
turingpost.com
·
3d
3 days ago
Actions for Posting for authoring
Mechanistic
Analysis
of
Alignment
Algorithms in Language Models
🎭
AI Simulators
Content type:
Academic
arxiv.org
·
22h
22 hours ago
Actions for Mechanistic Analysis of Alignment Algorithms in Language Models
Neglected Basics of
AI
Alignment
🛡️
AI Safety
lesswrong.com
·
3d
3 days ago
Actions for Neglected Basics of AI Alignment
EDPB meets with EU Commissioner McGrath and adopts common data breach notification template
🦋
ATProto
edpb.europa.eu
·
14h
14 hours ago
Actions for EDPB meets with EU Commissioner McGrath and adopts common data breach notification template
U.S. Dental Insurance Market Growth, Coverage Trends and Industry Forecast
🛡️
AI Safety
community.ops.io
·
2d
2 days ago
Actions for U.S. Dental Insurance Market Growth, Coverage Trends and Industry Forecast
AI
Pentesting Roadmap: Labs, Challenges, Writeups & Research
🎭
AI Simulators
Content type:
Blog
osintteam.blog
·
4d
4 days ago
Actions for AI Pentesting Roadmap: Labs, Challenges, Writeups & Research
How to Save/Export iPhone/iPad Text Messages to Computer. Windows/Mac compatible. Decipher TextMessage.
📝
Long-form Essays
Content type:
Video
deciphertools.com
·
20h
20 hours ago
Actions for How to Save/Export iPhone/iPad Text Messages to Computer. Windows/Mac compatible. Decipher TextMessage.
Cisco
AI
Defense Policy Studio: Turning Unwritten Policy into Adaptive
AI
Guardrails
🛡️
AI Safety
Content type:
Blog
blogs.cisco.com
·
1h
1 hour ago
Actions for Cisco AI Defense Policy Studio: Turning Unwritten Policy into Adaptive AI Guardrails
GDPR request
🔲
Are.na (https://www.are.na)
wiki.openfoodfacts.org
·
6d
6 days ago
Actions for GDPR request
Researchers develop
AI-powered
railway control system for efficient urban train operation
🤖
AGI
techxplore.com
·
13h
13 hours ago
Actions for Researchers develop AI-powered railway control system for efficient urban train operation
Understanding your paycheck in Workday
📝
Long-form Essays
Content type:
Academic
news.clemson.edu
·
1d
1 day ago
Actions for Understanding your paycheck in Workday
The
AI
models
finding 10,000 vulnerabilities are the same ones China is trying to copy. That is the problem.
🛡️
AI Safety
Content type:
News
thenextweb.com
·
2d
2 days ago
Actions for The AI models finding 10,000 vulnerabilities are the same ones China is trying to copy. That is the problem.
Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization
🛡️
AI Safety
Content type:
Academic
arxiv.org
·
22h
22 hours ago
Actions for Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization
I built a machine that turns
AI
papers into interactive explainers
🎭
AI Simulators
Content type:
Blog
blog.skz.dev
·
5d
5 days ago
Actions for I built a machine that turns AI papers into interactive explainers
Data retention practices for Mythos-class
models
| Claude Help Center
🛡️
AI Safety
support.claude.com
·
1d
1 day ago
·
Hacker News
Actions for Data retention practices for Mythos-class models | Claude Help Center
scMTG reconstructs single-cell temporal dynamics with Markov transition generators
🛡️
AI Safety
Content type:
Academic
biorxiv.org
·
3d
3 days ago
Actions for scMTG reconstructs single-cell temporal dynamics with Markov transition generators
« Page 1
·
Page 3 »
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