Consider the Ladder
Why do different AI models tell the same joke?
7-30-2024
You can’t bribe an LLM anymore, but does emotional blackmail still work?
Testing the guardrails of large language models and finding effective strategies to word around them.
6-25-2024
Comparing Large Language Models Side by Side
What can we learn from comparing large language models side by side and some initial findings.
6-18-2024