Offensive Rust

Feeds to Scour
SubscribedAll
Scoured 26 posts in 19.8 ms

No high-quality results found.

Less-relevant results

Security AI shouldn't only belong to the giants.

 🎖️Wargaming  Content type: Blog
dev.to··DEV

AMD reaches almost 45% CPU share in the latest Steam Hardware Survey for Windows gaming PCs — Ryzen is steadily gaining ground against Intel's legacy domination

 🎮Video Games  Content type: News
tomshardware.com
··Hacker News

How to Train Your (Dragons) Analysts

 💻WMI Abuse  Content type: Blog
trustedsec.com·

OceanLotus Hits Vietnam Investors With SPECTRALVIPER in FireAnt Attack

 💻WMI Abuse
thehackernews.com·

Three types of model organism

 🎯Pen Testing
lesswrong.com·

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

 💻WMI Abuse
malware.news·

Anthropic says internal and external red team tests of Fable 5 found no universal jailbreaks; it will keep user traffic for 30 days, aligning with Trump's AI EO...

 🎭Anthropic Claude
techmeme.com·

How I Hunted a Meterpreter C2 Session Using Sysmon

 ⚙️Kernel Callbacks  Content type: Blog
dev.to··DEV

US Army soldiers say you can't just pour AI on new warfighting tech like ranch dressing

 💻Tech News  Content type: News
businessinsider.com
·

DEW #159 - Synthetic Logs for Detection, Device Code Phishing Detection & Mythos 5 release

 🎭Social Engineering  Content type: News
detectionengineering.net·

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

 🕳LLM Vulnerabilities  Content type: Discussion
langprotect.com··DEV

How to reduce capability degradation from off-model SFT

 🧠Context Engineering
lesswrong.com·

Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards

 🧠Claude
thehackernews.com·

Title: SecurAI Sentinel: The AI-Powered Ops Dashboard Bridging Intelligence and Orchestration

 🔐Infosec  Content type: Blog
dev.to··DEV

Anthropic says Mythos is too dangerous for the public. It just gave 150 more organisations access.

 🔒Information Security  Content type: News
thenextweb.com·

Anthropic says these topics are too dangerous to let its Fable 5 model talk about

 🧠Claude  Content type: News
arstechnica.com·

Tracing Eval-Awareness Emergence Through Training of OLMo 3

 🎯RLHF
lesswrong.com·

Why a single AI confidently lies to you — and a council doesn't

 🛡️Penetration Testing  Content type: Blog
dev.to··DEV

Week 10 & 11

 🔒Security  Content type: Blog
dev.to··DEV

Securing AI Systems: Red Teaming, Prompt Injection, and Adversarial Testing

 🛡️LLM Security  Content type: Blog
dev.to··DEV

No more posts from buckman's subscribed feeds.

Scour all 25258 feedsLearn more about Feeds

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