https://nlpurr.github.io/posts/a-collection-of-good-llm-analogies/https://nlpurr.github.io/posts/case-of-llm-evals/https://nlpurr.github.io/posts/gender-bias-in-gpt4-a-short-demo/https://nlpurr.github.io/posts/no-sally-anne-pass-for-gpt4/https://nlpurr.github.io/posts/prompt-cap/https://nlpurr.github.io/posts/rethinking-user-study-design-for-evaluating-model-explanations-a-sketchnote/https://nlpurr.github.io/posts/can-rationalization-improve-robustness-a-sketchnote/https://nlpurr.github.io/posts/beware-the-rationalization-trap-a-sketchnote/https://nlpurr.github.io/https://nlpurr.github.io/collections/posts/https://nlpurr.github.io/collections/sketchnotes/