Lockdown Mode
41 points
3 hours ago
| 6 comments
| help.openai.com
| HN
simonw
1 hour ago
[-]
On the one hand this is exactly the right solution to prevent lethal trifecta exfiltration attacks.

The existence of lockdown mode does however imply that ChatGPT, in its default settings, does not provide robust protection against sufficiently determined data exfiltration attacks!

reply
berlianta
1 hour ago
[-]
Related: Simon Willison’s post on OpenAI’s new Lockdown Mode (he coined the “lethal trifecta” term this is based on): https://simonwillison.net/2026/Jun/5/openai-help-lockdown-mo...
reply
jameshart
46 minutes ago
[-]
Related: simonw is Simon Willison
reply
berlianta
25 minutes ago
[-]
Yeah I know the source references him (replying to his comment), that's exactly why I'm giving credit where it's due
reply
Noumenon72
21 minutes ago
[-]
I hadn't realized that deep research or generating images that I paste into Twitter were possibly exfiltrating my data. Yikes.
reply
varenc
3 hours ago
[-]
Probably influenced by Apple's feature with the same name: https://support.apple.com/en-us/105120

I imagine that enterprise companies will be quite interested in this.

reply
rafram
3 hours ago
[-]
reply
throwaway27448
37 minutes ago
[-]
Somehow he comes off as even less human than zuck
reply
ares623
3 hours ago
[-]
i can definitely feel the agi now
reply
neonstatic
2 hours ago
[-]
Congratulations, you are a high taste tester!
reply
zerobees
52 minutes ago
[-]
"Prompt injection is not currently a major risk, but its impact could grow as attackers develop more sophisticated methods." - that's such a weird statement to make. It's one of the most significant factors limiting the adoption of the technology in business.

I have mixed feelings about this feature. We're playing with tech that's supposed to do human-shaped things but can't be trusted nearly as much as a human employee (and can't be held responsible for what it does). Restricting the tools available to that patently untrustworthy entity doesn't solve the problem, it just makes the entity less useful, forcing you to sooner or later let it out of the jail.

reply
kijin
2 hours ago
[-]
So we still don't have a reliable way to separate instructions from data when talking to an LLM, a problem that humans learned how to solve decades ago in areas like SQL and memory safety. But hey, we have these hopefully-not-leaky containers, which are probably implemented with just more system prompts.

How long until somebody figures out how to trick Codex into disabling Lockdown Mode for you?

reply
mapontosevenths
1 hour ago
[-]
> So we still don't have a reliable way to separate instructions from data when talking to an LLM

Humans also do not know how to do this reliably, which is why phishing is still a thing and always will be.

reply
Smaug123
1 hour ago
[-]
I think the Stroop effect ("read these colour names, each written in a different colour") is probably the purest demonstration of this. Humans are trivially prompt-injectable.
reply
dnnddidiej
2 hours ago
[-]
We can seperate them but the $ value of an agent that does is much lower than one that doesn't.

As a pre LLM analogy imagine working at a bank with a whitelist firewall. You need to install a package but requires an IT ticket. Safer but slooooower.

Now not saying what the answer here is but that is the issue.

The answer may be more like industries that get safer through lessons (like aviation) rather than go for 100% safety out of the gate. Because both fast travel and AI agents are insanely useful.

reply
altmanaltman
2 hours ago
[-]
what? Aviation safety is not designed to get safer through lessons? They literally try to ensure it is 100% safe out of the gate. The accidents that happen are usually statistical outliers and lead to loss of life.

That's what it means when they say aviation regulations are written in blood. Not that they just fling planes into the sky and be like "boy i hope we learn some new regulations from this". The number of airplane crashes would be astronomically larger if the 100% safety part was not embedded into the design process.

reply
dnnddidiej
1 hour ago
[-]
I think we agree? Unless my reading comp is off today.
reply
madanparas
2 hours ago
[-]
The help doc explicitly carves out Codex: "Lockdown Mode does not affect network access in Codex." The mode limits outbound requests in chat to block prompt injection exfiltration, but Codex network access is a separate setting. An enterprise team that turns on Lockdown Mode while using Codex against internal repos still has an open outbound path this mode doesn't cover.
reply