There are dozens of cognitive biases. There are dozens of cognitive biases. And even knowing a few gives you a powerful edge. Each one is a tool in your content creation toolkit. To use them effectively, you need to understand your audience's psychology. (Btw, AI can help.)
PROMPT ENGINEERING
-
AI Models’ Remarkable Image Analysis and Geolocation Inference Capabilities
By
–
The ability of the AI to make very educated guesses from images is underrated and never ceases to amaze me. Both Claude 3 and GPT-4 figure out I was likely in Monterrey from a picture of a sea otter and a small amount of architecture (pictures were from me, not in training.)
-
Midjourney Launches URL Reference Feature for Character Consistency
By
–
Midjourney just launched a feature to reference URLs to create character consistency within outputs.
— Rowan Cheung (@rowancheung) 12 mars 2024
This is huge. Been waiting on this since forever.
Doing a step-by-step tutorial and top tips in tomorrow's newsletter: https://t.co/Gm5KwesnA7pic.twitter.com/deNmxC7e89Midjourney just launched a feature to reference URLs to create character consistency within outputs. This is huge. Been waiting on this since forever. Doing a step-by-step tutorial and top tips in tomorrow's newsletter: https://
therundown.ai/subscribe -
RepoToTextForLLMs: Convert GitHub repos to text for LLMs
By
–
In the era of long-context LLMs, I needed a way to quickly convert a GitHub repo into a text file to feed as a prompt.
— Pietro Schirano (@skirano) 11 mars 2024
Introducing RepoToTextForLLMs 📖
Not only does it return the full repo in one file, but it also appends a super prompt for analysis and understanding 👇 pic.twitter.com/WovzRUpzLeIn the era of long-context LLMs, I needed a way to quickly convert a GitHub repo into a text file to feed as a prompt. Introducing RepoToTextForLLMs Not only does it return the full repo in one file, but it also appends a super prompt for analysis and understanding
-
Master LLM Fine-Tuning: A Comprehensive Guide to Benefits and Implementation
By
–
Ready to master #LLM fine-tuning? Check out our definitive guide: Benefits of #FineTuning and when to do it How to prepare your #data set What it takes to manage training + serving #infra How to reliably and #efficiently fine-tune
-
Try Botsonic Free Tool from WriteSonic Platform
By
–
Try Botsonic at @WriteSonic — Start for FREE at https://
writesonic.com/botsonic?via=k
irk82
… -
Using ChatGPT to process and clean prompt text
By
–
Yup, just feed it first to ChatGPT and ask to ´remove xml tags”, it will make the prompt look normal and you will be able to use it!
-
AI ideation capabilities: recombinant novelty vs true innovation
By
–
I am missing context, it looks like the 2nd phase of the ideation GPT, which is the most grounded, since it involves web search. There are six steps, so you may want to wait until the end. In any case, AI is good at recombinant novelty and idea fluency, not all forms of novelty.
-
Anthropic Prompt Engineering Guide Techniques Overview
By
–
Very useful. Thanks for adding that in here! They also have a full guide going in-depth on each technique: https://
docs.anthropic.com/claude/docs/pr
ompt-engineering
… -
Claude AI Tutorials and Use Cases Expansion
By
–
Glad you found this one helpful – lots more Claude tutorials to come (finding SO many use cases)