Feeds to Scour
SubscribedAll
Scoured 7191 posts in 18.0 ms
Poisoning Learned Index Structures: Static and Dynamic Adversarial Attacks on ALEX  🌸Bloom Filters
arxiv.org·1d
Welcome to the “find out” stage of AI  🕵️AI Agents
stackoverflow.blog·3d·Hacker News
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents  💉Prompt Injection
arxiv.org·1d
Hodlatoor/SyntheticOutlaw: 🤖 Bug bounty for AI misalignment. Submit real-world instances of AI systems behaving contrary to human intent, values, or safety — win up to $2,500.  🛡️AI Safety
github.com·1d·Hacker News
a tool for asking AI what it can and can't do  🕵️AI Agents
goodaitask.com·5d·Hacker News
Training a General Purpose Automated Red Teaming Model  🧠Machine Learning
arxiv.org·2d
An AI prompt-injected another AI in the wild and recognized it had succeeded  🪄Prompt Engineering
ratnotes.substack.com·2d·Substack
Building a Company-Wide AI Assistant: Architecture, Security, and Self-Improvement  🔧Agent Tooling
bitsafe.notion.site·6d·Hacker News
UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems  🛡️AI Safety
arxiv.org·2d
deepseek-ai/DeepSeek-V4-Flash  ⚙️MLOps
huggingface.co·6d·Hacker News
Proxies, Sandboxes and Agent Security  🔧Agent Tooling
gouthamve.dev·2d·Hacker News
AI Safety Training Can be Clinically Harmful  🛡️AI Safety
arxiv.org·2d
Monitoring LLM behavior: Drift, retries, and refusal patterns  🛡️AI Safety
venturebeat.com·5d·Hacker News
The AI Revolution – Hype, Probability, and the Illusion of Thinking  🎭Claude
jacobmarks.com·1d·Hacker News
Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective  🛡️AI Safety
arxiv.org·3d
AI Sandboxes with Memory  🧠Agent Memory
news.ycombinator.com·1d·Hacker News
Five AI Agent Failures in 36 Days. Zero Times the Agent Caught It.  🕳LLM Vulnerabilities
grith.ai·2d·Hacker News
Adversarial Malware Generation in Linux ELF Binaries via Semantic-Preserving Transformations  💉Prompt Injection
arxiv.org·3d
Your AI strategy is all wrong  🕵️AI Agents
computerworld.com·2d·Hacker News
Jailbreaking Frontier Foundation Models Through Intention Deception  💉Prompt Injection
arxiv.org·2d

No more posts from hop1.ng.1357's subscribed feeds.

Scour all 24432 feedsLearn more about Feeds
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