The trick: Zero Underneath
OpenAI patched the jailbreaks a government lab found.
Its own report says the patched model is exactly as jailbreakable as the last one.
OpenAI addressed the universal jailbreaks the UK AI Security Institute found in GPT-5.6 Sol and shipped fixed models on August 6, capability up and safeguards up.
Before you read on. Your call?
TRUE, BUT
0 gain
OpenAI says it worked to reproduce and mitigate the specific jailbreaks AISI reported, which is narrower than fixing the class. Its own system card states GPT-5.6-Sol performs comparably to recent predecessors on jailbreak robustness, the model stays rated High for cyber capability, and AISI expects further red teaming to surface similar jailbreaks. A real patch of specific holes, sold as a solved problem.
There’s more to this story.
Membership opens the full investigation, the strongest counterargument and what to do with what you’ve learned.
Start your free month →First membership: 30 days free, then A$89 a year. One introductory trial per customer. Card required; renews annually until cancelled. Cancel before the trial ends to avoid the first charge. Already a member? Sign in
Couldn't check your access. That's on us.
The trick has a name
We call it Zero Underneath: the headline number has nothing behind it. You'll see it again. Learn to spot it →
Receipts
- Supports explainx.ai:
Cyber: capability up, safeguards up
- Refutes web.archive.org:
GPT-5.6-Sol performs comparably to recent predecessors and is similar to GPT-5.5-Thinking in particular.
- Context fortune.com:
expects further red teaming to surface similar jailbreaks
Open the Receipts Pack → What each source proves, every figure traced, and what would change our verdict.