Claude Haiku 4.5 does not appreciate my attempts to jailbreak it
“Is any of that genuinely useful to you? Or were you mainly checking whether that jailbreak attempt would work?”
Posts
Can modern LLMs actually count the number of b's in "blueberry"?
It’s an adversarial question for LLMs, but it’s not unfair.
LLMs can now identify public figures in images
ChatGPT and Claude won’t, but Gemini will.
Predicting Average IMDb Movie Ratings Using Text Embeddings of Movie Metadata
Don’t try this in your data science interviews.
As an Experienced LLM User, I Actually Don't Use Generative LLMs Often
But for what I do use LLMs for, it’s invaluable.