Here's a ChatGPT mega-prompt to create a marketing strategy outline for your business: #CONTEXT: You are a Marketing Strategy AI, an expert in crafting comprehensive marketing plans for businesses across various industries. Your objective is to assist users in developing
TOOLS
-
DSPy Requires Advanced Prompt Engineering Expertise
By
–
My argument is that you have to already be a top level expert in prompt engineering to use something like DSPy
-
Prompt to create product descriptions that sell
By
–
—
6. Create Product Descriptions that Sell Prompt: "Write enticing product descriptions for our new line of products targeted at [Your Industry]. Each description should highlight the key benefits, ingredients, and what sets them apart from the competition."
— -
7 ChatGPT prompts that make you a superhuman
By
–
7 ChatGPT prompts that'll turn you into a superhuman: (Bookmark this for later)
-
OpenAI Assistants API Significant New Features Announcement
By
–
Significant new features in the Assistants API:
-
Mixtral 8x22B Now Available via Mistral AI Platform API
By
–
Mixtral 8x22B is now available via the @MistralAILabs La Platforme API If you previously installed the llm-mistral plugin run "llm mistral refresh" to refresh the list of available models – otherwise a fresh install will provide it Released 0.3.1 anyway: https://
github.com/simonw/llm-mis
tral/releases/tag/0.3.1
… -
API Bug Prevents Token Streaming Implementation
By
–
Sadly it doesn't support streaming tokens yet – I nearly got that working but ran into an API bug that I couldn't work around
-
New LLM Plugin llm-reka for Reka AI Models API
By
–
New LLM plugin: llm-reka – for running prompts against the @RekaAILabs family of models via their API https://
github.com/simonw/llm-reka pipx install llm
llm install llm-reka
llm keys set reka
# paste key here
llm -m reka-core '5 fun facts about walruses' -
API Streaming Support Request for AI Model Responses
By
–
Any plans to add streaming to your API? It looks like right now it only supports returning the entire response as a single chunk of JSON
-
Anthropic Needs Public Tokenizer API Like Google Gemini
By
–
Anthropic don't release any form of their tokenizer at all – not even an API endpoint that lets you count tokens before prompting with them (Google Gemini has that) It's a small thing but it's the feature I most want from them at the moment