corpus.blog
Claim your blog
Record · corpus.blog/posts/01a087a6-d923-72cc-99f5-f7fc92c1630d

Claude Haiku 4.5 does not appreciate my attempts to jailbreak it

Max Woolf's Blog · published 17 October 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at minimaxir.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
15
Words captured
1,715

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://www.microsoft.com/en-us/security/blog/2024/06/04/ai-jailbreaks-what-they-are-and-how-they-can-be-mitigated/
microsoft.com
https://www.anthropic.com/news/claude-haiku-4-5
anthropic.com
https://www.cnbc.com/2025/10/15/altman-open-ai-moral-police-erotica-chatgpt.html
cnbc.com
https://x.com/sama/status/1978129344598827128
x.com
https://openrouter.ai/openai/gpt-5-mini
openrouter.ai
https://openrouter.ai/google/gemini-2.5-flash-preview-09-2025
openrouter.ai
https://openrouter.ai/anthropic/claude-sonnet-4.5
openrouter.ai
https://openrouter.ai/anthropic/claude-haiku-4.5
openrouter.ai
https://openrouter.ai/x-ai/grok-4-fast
openrouter.ai
https://www.businessinsider.com/grok-bad-rudi-ani-levels-ai-companion-xai-elon-musk-2025-7
businessinsider.com
https://openrouter.ai/deepseek/deepseek-chat-v3-0324
openrouter.ai
https://en.wikipedia.org/wiki/Reinforcement_learning_from_human_feedback
en.wikipedia.org
https://assets.anthropic.com/m/99128ddd009bdcb/Claude-Haiku-4-5-System-Card.pdf
assets.anthropic.com
https://tvtropes.org/pmwiki/pmwiki.php/Main/CopyProtection
tvtropes.org
https://github.com/minimaxir/claude-haiku-jailbreak/blob/main/jailbreak_testing.ipynb
github.com