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 safety
🛡 LLM safety
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
372
posts in
9.2
ms
OpenAI Help: Lockdown
Mode
🛡️
Red Teaming
simonwillison.net
·
5d
5 days ago
Actions for OpenAI Help: Lockdown Mode
Meta’s
AI
Support Hack Is a Warning for Every
Team
Automating User Access
🛡️
Red Teaming
Content type:
Discussion
langprotect.com
·
3d
3 days ago
·
DEV
Actions for Meta’s AI Support Hack Is a Warning for Every Team Automating User Access
Microsoft releases incident response playbook for Copilot and Azure
AI
🛡️
Red Teaming
4sysops.com
·
2d
2 days ago
Actions for Microsoft releases incident response playbook for Copilot and Azure AI
Models
May Behave Worse When Eval Aware
🎯
AI Alignment
lesswrong.com
·
12h
12 hours ago
Actions for Models May Behave Worse When Eval Aware
Infosec News Nuggets — June 9, 2026
🛡️
Red Teaming
aboutdfir.com
·
2d
2 days ago
Actions for Infosec News Nuggets — June 9, 2026
The
AI
automation tool nobody talks about just replaced my entire workflow setup
🛡️
Red Teaming
xda-developers.com
·
3d
3 days ago
Actions for The AI automation tool nobody talks about just replaced my entire workflow setup
Show HN:
Jailbreak
this
model
to get 3B tokens
🛡️
Red Teaming
opir.ai
·
22h
22 hours ago
·
Hacker News
Actions for Show HN: Jailbreak this model to get 3B tokens
OpenAI unveils Lockdown
Mode
to protect sensitive data from
prompt
injection
attacks
🛡️
Red Teaming
techcrunch.com
·
5d
5 days ago
·
Hacker News
Actions for OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
Data Loss Prevention - Define custom topics for
AI
prompt
protection
🛡️
Red Teaming
developers.cloudflare.com
·
22h
22 hours ago
Actions for Data Loss Prevention - Define custom topics for AI prompt protection
Particle: Anthropic Releases Claude Fable 5, a Guardrailed Public Version of Mythos
🛡️
Red Teaming
Content type:
News
particle.news
·
2d
2 days ago
Actions for Particle: Anthropic Releases Claude Fable 5, a Guardrailed Public Version of Mythos
One
Jailbreak
, Many Tongues: Learning
Language-Insensitive
Intention Representations for Multilingual
Jailbreak
Detection
🛡️
Red Teaming
Content type:
Academic
arxiv.org
·
18h
18 hours ago
Actions for One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection
Why OpenAI is disabling ChatGPT web access to fight
prompt
injection
attacks
🛡️
Red Teaming
Content type:
News
livemint.com
·
4d
4 days ago
Actions for Why OpenAI is disabling ChatGPT web access to fight prompt injection attacks
Siri
AI
is a Malware Vector
🛡️
Red Teaming
Content type:
Blog
loufranco.com
·
2d
2 days ago
·
Hacker News
Actions for Siri AI is a Malware Vector
Inside ChatGPT’s New Lockdown
Mode
: Is Your Data
Safer
?
🛡️
Red Teaming
telecomtalk.info
·
3d
3 days ago
Actions for Inside ChatGPT’s New Lockdown Mode: Is Your Data Safer?
Love Teaching? ByteByteGo Is Hiring Part-Time
AI
& Engineering Instructors
🛡️
Red Teaming
Content type:
News
Content type:
Blog
blog.bytebytego.com
·
1d
1 day ago
Actions for Love Teaching? ByteByteGo Is Hiring Part-Time AI & Engineering Instructors
New ChatGPT Lockdown
Mode
Limits Tools That Could Enable Data Exfiltration
🛡️
Red Teaming
thehackernews.com
·
5d
5 days ago
Actions for New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration
Matador-og/huntbot:
AI
offensive security harness for bug bounty, pentesting,
red
teaming
.
🛡️
Red Teaming
Content type:
Code
github.com
·
1d
1 day ago
·
Hacker News
Actions for Matador-og/huntbot: AI offensive security harness for bug bounty, pentesting, red teaming.
OpenAI Announces Unnerving New ChatGPT Feature Named ‘Lockdown
Mode
’
🛡️
Red Teaming
gizmodo.com
·
4d
4 days ago
Actions for OpenAI Announces Unnerving New ChatGPT Feature Named ‘Lockdown Mode’
Mathematical proof reveals why fixed
AI
guardrails can never block every
jailbreak
🛡️
Red Teaming
techxplore.com
·
1d
1 day ago
Actions for Mathematical proof reveals why fixed AI guardrails can never block every jailbreak
Neglected Basics of
AI
Alignment
🎯
AI Alignment
lesswrong.com
·
4d
4 days ago
Actions for Neglected Basics of AI Alignment
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