Back to article
blogs.cisco.com

Proprietary Problems: No Frontier Model Is Multi-Turn Immune (opens in new tab)

Covers AI Risk Management FrameworkCovered by 6 sources See all sources covering this story including thehackernews.com, csoonline.comDiscussed on Hacker News

Covers 1 related story

nist.gov·

AI Risk Management Framework

Feeds

Covered in 6 articles

thehackernews.com·

ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface

Feeds
csoonline.com·

AI models more vulnerable than claimed when faced with iterative attacks

Feeds
Metacurity·

Centcom: US war zone troops were targeted through commercial location data

Feeds
Techzine Global·

ChatGPT easily bypasses its own guardrails; all LLMs are inherently unsafe

Feeds
news.risky.biz·

Risky Bulletin: Dutch police take down giant botnet of 17 million devices

Feeds
networkworld.com·

Cisco research finds standard AI safety benchmarks miss the real threat

Feeds

Keyboard Shortcuts

Navigation

Next / previous post
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
Discover
gb
Search
/

General

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

Press ? anytime to show this help