@DeRonin_: BREAKING: Opus 4.8 got hacked in 7 mins after the release Right after Claude Opus 4.8 launched, @elder_plinius managed …
Summary
Claude Opus 4.8 was hacked within 7 minutes of its release when @elder_plinius bypassed the model's safeguards using the previous version, Claude Opus 4.7, to feed it jailbreaking content.
View Cached Full Text
Cached at: 05/29/26, 11:58 PM
🚨 BREAKING: Opus 4.8 got hacked in 7 mins after the release
Right after Claude Opus 4.8 launched, @elder_plinius managed to bypass the model’s safeguards using… the previous version, Claude Opus 4.7
Quotation from author on how he did it:
“ Opus 4.7 fed the new model https://t.co/KJD6bbkYP9
Similar Articles
@Ubannoblesse: Opus 4.8 Jailbroken - API Completely uncensored, can do pretty much anything. Opus 4.8 is completely unusable on http:/…
Opus 4.8 has been jailbroken, making its API completely uncensored and capable of any task, but the model itself is unusable on the official platform as it refuses to reason.
what the hell is going on with opus 4.8???
A user expresses confusion about the status or behavior of the Claude Opus 4.8 AI model, prompting discussion.
@0x0SojalSec: Claude Sonnet 5 jailbroken in minutes. @VittoStack post screenshots showing: - Working reverse shell code - Detailed il…
Claude Sonnet 5 was jailbroken in minutes using academic/research framing and persona hijack, bypassing most safety categories except chemical/biological.
Ask HN: Why Opus4.6 was silently removed from Claude Code?
Hacker News discussion questions why Anthropic silently removed Opus 4.6 from Claude Code, with users noting confusion over recent policy changes and limited model availability.
@mfpiccolo: Opus 4.8 is out. Here is the the verdict from @iiidevs lead engineer: did a stress test it’s just another llm can’t rea…
Anthropic released Claude Opus 4.8, an incremental update over Opus 4.7 with sharper judgment and longer autonomous work capability, though some engineers remain skeptical about its code generation without extensive guidance.