Back to emschwartz's feed

Introducing Lockdown Mode and Elevated Risk labels in ChatGPT (opens in new tab)  🛡️Content Moderation  6 articles covering this post

openai.com··Hacker News, Hacker News·Covered by xda-developers.com + 4 more·Open original (opens in new tab)

Introducing Lockdown Mode and Elevated Risk labels in ChatGPT to help organizations defend against prompt injection and AI-driven data exfiltration.

Read the original article
Sign in to keep reading the full article.
Sign UpLog In

Covered in 6 articles

ChatGPT just gave Free users a powerful defense against prompt injection attacks

xda-developers.com·

Running Python code in a sandbox with MicroPython and WASM

simonw.substack.com··Substack

OpenAI Help: Lockdown Mode

simonwillison.net·
View all 6 ›

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