PromptLayer reposted this
8 new Anthropic prompting tips I learned from Zack Witten (Anthropic's prompt engineer): Tip #1: Use XML tags to structure prompts Tip #2: Be specific with instructions rather than saying "be concise" Tip #3: Mimic desired tone of response in your prompt Tip #4: Proofreading your prompts matters Tip #5: Write prompts in a language you know well Tip #6: Use Claude prefills to force JSON response Tip #7: Use negative prompting sparingly Tip #8: Rely more on human messages than system messages Thanks to Anthropic's "Prompt Doctor" for the great workshop at AI Engineer 🙏 More details on each tip here in the full blog post: https://lnkd.in/edvcCWix Original workshop available here: https://lnkd.in/eVmAn9nc
Some great, easy to apply tips in this blog post!
Thanks for sharing
Great stuff, thanks for sharing.
Working on 🛰️ Answer HQ // ex: pinecone, infinitus, oracle cloud, singlestore, looker (acq. google cloud)
1mofyi "Use XML tags to structure prompts" is specific to anthropic's claude, because that's how they finetuned their models. iirc, this isn't the case for the majority of other models. correct me if i am wrong though.