I always enjoy examples of prompt artists thinking they can beg their way of the LLM's janky behaviour.
> Critical UI Requirements
> Therefore, you SHOULD ALWAYS test your completion requests first in the analysis tool before building an artifact.
> To reiterate: ALWAYS TEST AND DEBUG YOUR PROMPTS AND ORCHESTRATION LOGIC IN THE ANALYSIS TOOL BEFORE BUILDING AN ARTIFACT THAT USES window.claude.complete.
Maybe if I repeat myself a third time it'll finally work since critical, ALL CAPS and "reiterating" didn't cut the mustard.
I really want this AI hype to work for me so I can enjoy all the benefits but I can only be told 'you need to write better prompts' so many times when I can't see how that's the answer to these problems.
I would think someone working for Anthropic would be quite aware of this too.
Either fix the prompt until it behaves consistently, or add conventional logic to ensure desired orchestration.
For example, Grok will interpret "BE RIGHT" as an imperative command to inject White Supremacist Ideology and Holocaust Denial into dialogs about quantum physics and children's bedtime stories.
https://news.mit.edu/2024/large-language-models-dont-behave-...
Claude tipped me off about the name of that section as part of its thinking process in answer to my first question.
> ALWAYS include ALL messages from the beginning of the conversation up to the current point.
That doesn't seem very scalable.
More of my notes here: https://simonwillison.net/2025/Jun/25/ai-powered-apps-with-c...
I'm amused that Anthropic turned "we added a window.claude.complete() function to Artifacts" into what looks like a major new product launch, but I can't say it's bad marketing for them to do that!