LLM Security

Feeds to Scour
SubscribedAll
Scoured 667 posts in 8.2 ms

Claude vs GPT-4: Which AI API Is Better for Developers? (2026)

 🤖AI
kalyna.pro··DEV

What it looks like: Trusted, compliant AI systems at scale - Azure AI Tech Accelerator

 🤖AI
techcommunity.microsoft.com·

Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets

 🔓Pentest  Content type: Blog
varonis.com··Hacker News

Gemini Voice Assistant Hijacked via Messaging Notifications

 🔒CyberSecurity
securityweek.com·

Microsoft releases incident response playbook for Copilot and Azure AI

 💥Binary Exploitation
4sysops.com·

NVIDIA Accelerates Google DeepMind’s DiffusionGemma for Local AI

 🤖AI  Content type: Blog
blogs.nvidia.com·

Neglected Basics of AI Alignment

 🤖AI
lesswrong.com·

Apple's AI Can Now Change Your Passwords. What Could Possibly Go Wrong?

 🔒CyberSecurity  Content type: Blog
kylereddoch.me··Hacker News

The biggest local LLM on your machine is useless if it can't call a single tool, no matter how many parameters it has

 🤖AI
xda-developers.com·

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

 🔒CyberSecurity
thehackernews.com·

Siri AI is a Malware Vector

 🤖AI  Content type: Blog
loufranco.com··Hacker News

Pro Wrestlers Are Fighting in Libraries Now, and It’s Actually for a Good Cause

 🔒CyberSecurity  Content type: News
vice.com·

2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash, and MTP

 💥Binary Exploitation  Content type: Blog
dnhkng.github.io·

Intelligent inference scheduling with llm-d on Red Hat AI

 💥Binary Exploitation
developers.redhat.com·

Comprehensive evaluation of LLM capabilities for interpretation and analysis of genome-scale metabolic models in metabolic engineering

 💥Binary Exploitation  Content type: Academic
biorxiv.org·

Fake Context Alignment: The Attack That Made Gemini Obey Strangers Through Your Notifications

 🔒CyberSecurity
securityaffairs.com·

Show HN: Jailbreak this model to get 3B tokens

 💥Binary Exploitation
opir.ai··Hacker News

Assessing Automated Prompt Injection Attacks in Agentic Environments

 🔓Pentest  Content type: Academic
arxiv.org·

Hackers could use poisoned WhatsApp and Slack notifications to take over your Google Gemini – and make it work on their behalf

 🔒CyberSecurity
techradar.com
·

Anthropic's Fable Jailbreak (Circumvent safety nets)

 💥Binary Exploitation  Content type: Code
github.com··Hacker News
Sign up or log in to see more results
Sign UpLogin

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