LLM safety

Feeds to Scour
SubscribedAll
Scoured 372 posts in 9.2 ms

OpenAI Help: Lockdown Mode

 🛡️Red Teaming
simonwillison.net·

Meta’s AI Support Hack Is a Warning for Every Team Automating User Access

 🛡️Red Teaming  Content type: Discussion
langprotect.com··DEV

Microsoft releases incident response playbook for Copilot and Azure AI

 🛡️Red Teaming
4sysops.com·

Models May Behave Worse When Eval Aware

 🎯AI Alignment
lesswrong.com·

Infosec News Nuggets — June 9, 2026

 🛡️Red Teaming
aboutdfir.com·

The AI automation tool nobody talks about just replaced my entire workflow setup

 🛡️Red Teaming
xda-developers.com·

Show HN: Jailbreak this model to get 3B tokens

 🛡️Red Teaming
opir.ai··Hacker News

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

 🛡️Red Teaming

Data Loss Prevention - Define custom topics for AI prompt protection

 🛡️Red Teaming
developers.cloudflare.com·

Particle: Anthropic Releases Claude Fable 5, a Guardrailed Public Version of Mythos

 🛡️Red Teaming  Content type: News
particle.news·

One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection

 🛡️Red Teaming  Content type: Academic
arxiv.org·

Why OpenAI is disabling ChatGPT web access to fight prompt injection attacks

 🛡️Red Teaming  Content type: News
livemint.com·

Siri AI is a Malware Vector

 🛡️Red Teaming  Content type: Blog
loufranco.com··Hacker News

Inside ChatGPT’s New Lockdown Mode: Is Your Data Safer?

 🛡️Red Teaming
telecomtalk.info·

Love Teaching? ByteByteGo Is Hiring Part-Time AI & Engineering Instructors

 🛡️Red Teaming  Content type: News  Content type: Blog
blog.bytebytego.com·

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

 🛡️Red Teaming
thehackernews.com·

Matador-og/huntbot: AI offensive security harness for bug bounty, pentesting, red teaming.

 🛡️Red Teaming  Content type: Code
github.com··Hacker News

OpenAI Announces Unnerving New ChatGPT Feature Named ‘Lockdown Mode

 🛡️Red Teaming
gizmodo.com·

Mathematical proof reveals why fixed AI guardrails can never block every jailbreak

 🛡️Red Teaming
techxplore.com·

Neglected Basics of AI Alignment

 🎯AI Alignment
lesswrong.com·
Sign up or log in to see more results

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
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
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help