Adding “think step by step” in prompts can yields better outputs. Anthropic says that giving the chatbot a role like “data scientist” makes for different results, because a data scientist might see different things in data. Now, models are not using language, but a numerical representation: tokens. 17509, 656, 5983 is “step by step” tokenized...
Tags prompts (22)
Instant voice cloning, on a MacBook Air, for free, no Elevenlabs
Chinese e‑commerce giant Alibaba has released new Qwen models for generating and cloning voices earlier this year. Which means: With only a couple of seconds of recorded material, we can generate a cloned voice recording. On a four year old MacBook Air. Instantly. At no cost. This used to be the domain of Elevenlabs. The...
tropes.md is a one-file blacklist of AI writing tells for your system prompt.
Contrastive negation used to be a rhetorical device, now it screams “I used ChatGPT”
This is the future, not a newsletter. When you define something by saying what it's not, it's called "contrastive negation." Nowadays, it's a telltale of AI writing. You can see it all over Threads and LinkedIn. At the same time, the bros are feeding chatbots the Wikipedia definition of "AI writing" and telling them to...
Just send the prompt twice? A new paper argues that repeating helps non-reasoning models. There’s a catch: The models tested (4o, Claude 3.7) are retired by now.
Bring AI into your CMS with a Chrome plugin
This gets a little technical, but with AI's help it's straightforward. Here's how it works: a Chrome plugin grabs content from the CMS text fields, sends it to ChatGPT, Gemini, or Claude with various preset prompts, and displays the response right in the browser. For example: checking against your house style. A plausibility check. Suggestions...
How to use AI without getting dumb: Strategies for critical prompt design to keep AI from becoming a cheap shortcut or decision-maker. (Paul Bradshaw, Online Journalism Blog)
How to get less hallucinations: “What often is deemed a ‘wrong’ response is often merely a first pass at describing the beliefs out there. And the solution is the same: iterate the process.” (Mike Caulfield, The End(s) of Argument)
Make prompt engineering great again: A growing list of tools may help you improve your generative AI prompts, but sometimes all you need is a spreadsheet. (Clare Spencer, Generative AI in the Newsroom)
Case Study on iterative prompt evaluation and improvement: A workflow for targeted prompting to refine AI-generated newsletter headlines. (Ashlyn Wang, Generative AI in the Newsroom)
LLM journalism tool advisor: Tired of figuring out how to use AI in journalism? Joe Amditis has collected tools and prompts and built a practical interface.
Video: AI prompt engineering deep dive (Anthropic)
Leaked (?) prompt for generating system prompts on the playground (philschmid, GitHub)
The Prompt Report: A Systematic Survey of Prompting Techniques (Sander Schulhoff et.al., arxiv.org)
