Skip to main content
Scour
Discover
Docs
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
AI Safety
🛡️ AI Safety
model alignment, guardrails, responsible AI, AI red teaming
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
381
posts in
19.1
ms
🤖
AI Agents
GitHub
·
1d
1 day ago
Show HN: Lelu – gate OpenAI agent actions on confidence and
prompt
injection
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Show HN: Lelu – gate OpenAI agent actions on confidence and prompt injection
🤖
AI Agents
medium.com
·
3d
3 days ago
The Role of HR in
Responsible
AI
Adoption
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for The Role of HR in Responsible AI Adoption
🤖
AI Agents
EDB
·
1d
1 day ago
Inside EDB’s New Principles for
Responsible
AI
: Sovereign, Governed, Trusted and Beneficial
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Inside EDB’s New Principles for Responsible AI: Sovereign, Governed, Trusted and Beneficial
đź§
LLMs
Above the Law
·
8h
8 hours ago
No Points For Held Tongues — See Also
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for No Points For Held Tongues — See Also
🔌
MCP
arcade.dev
·
2d
2 days ago
Beyond Enterprise-Managed Authorization for MCP
CoversÂ
3Â stories
See all stories this covers
 includingÂ
Open Policy Agent - Homepage | Open Policy Agent
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Beyond Enterprise-Managed Authorization for MCP
đź”—
APIs
ryandens.github.io
·
4d
4 days ago
Promptblock
– detect prompt
injections
in GitHub issues
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Promptblock – detect prompt injections in GitHub issues
đź§
LLMs
Turing Post
·
1d
1 day ago
AI
Agents in 2026: Local, Physical,
Responsible
AI
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for AI Agents in 2026: Local, Physical, Responsible AI
đź“Š
LLM Evaluation
arXiv
·
3h
3 hours ago
Adaptive Evaluation of Out-of-Band Defenses Against
Prompt
Injection
in LLM Agents
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents
✍️
Prompt Engineering
medium.com
·
6d
6 days ago
# Fictional Framing as a
Prompt
Injection
Vector: A Reproducibility Study on GPT-4o and Claude
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for # Fictional Framing as a Prompt Injection Vector: A Reproducibility Study on GPT-4o and Claude
⚙️
Backend Engineering
yongzx.github.io
·
2d
2 days ago
Surprising lessons from my research scientist job search
CoversÂ
ML Job Interviews: The Ultimate Guide
Covered byÂ
Data Science Weekly Newsletter
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Surprising lessons from my research scientist job search
✍️
Prompt Engineering
spandaimarketing.medium.com
·
14h
14 hours ago
Prompt
Injection
Was the Least Interesting Security Problem We Found
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Prompt Injection Was the Least Interesting Security Problem We Found
🤖
AI Agents
4sysops
·
22h
22 hours ago
DeepMind chief explores the intersection of AGI, simulation, and creativity
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for DeepMind chief explores the intersection of AGI, simulation, and creativity
⚙️
Backend Engineering
easternherald.com
·
3d
3 days ago
OrcaRouter Releases
AI
Threat Report 2026 and Makes Its Security Controls Free Amid Rise in
Prompt-Injection
Attacks
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for OrcaRouter Releases AI Threat Report 2026 and Makes Its Security Controls Free Amid Rise in Prompt-Injection Attacks
✍️
Prompt Engineering
Google
·
1d
1 day ago
Computer use in Gemini 3.5 Flash
CoversÂ
4Â stories
See all stories this covers
 includingÂ
Computer Use  | Gemini API  | Google AI for Developers
Covered byÂ
12Â sources
See all sources covering this story
 includingÂ
The Rundown AI
,
Android Authority
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Computer use in Gemini 3.5 Flash
✍️
Prompt Engineering
sh.itjust.works
·
12h
12 hours ago
New Gaslight macOS Malware Uses
Prompt
Injection
to Disrupt
AI-Assisted
Analysis
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis
đź§
LLMs
Bloomberg
·
3d
3 days ago
Tech Disruptors: Invisible Technologies on
RLHF
and LLM
Training
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Tech Disruptors: Invisible Technologies on RLHF and LLM Training
đź”—
APIs
Docs
·
3h
3 hours ago
Can We Talk About the "
AI/ML
Engineer" Shortcut for a Second?
Discussed on
DEV
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Can We Talk About the "AI/ML Engineer" Shortcut for a Second?
🤖
AI Agents
tehnologijaviews.medium.com
·
6d
6 days ago
Is the US Government’s Anthropic Ban Actually Helping the Brand? A Surprising Turn in
AI
Regulation
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Is the US Government’s Anthropic Ban Actually Helping the Brand? A Surprising Turn in AI Regulation
✍️
Prompt Engineering
medium.com
·
2d
2 days ago
Why
prompt
injection
works: a Transformer-level view
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Why prompt injection works: a Transformer-level view
🏗️
AI Infra
CNN
·
8h
8 hours ago
White House asks OpenAI to limit its next
model
release
Covered byÂ
lesnumeriques.com
Discussed on
Hacker News
Love
Like
Not for me
Save
See related topics
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for White House asks OpenAI to limit its next model release
« Page 1
·
Page 3 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous post
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
Discover
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
Like
Save
Not for me
Report