Three things that differentiate-
1) This is not a subscription, you buy it once and use forever (potentially free if you are using local models)
2) If you are using local models, all the data is on your device, we literally have no servers.
3) If you don't speak american english or have an accent while speaking English, whisperflow accuracy drops dramatically, here you can bring any API key, like I bring Sarvaam AI key which gives me far better results in Indian English and accent than whisperflow any other competitors.
Would you like to try it out and see for yourself?
We need society leaders who will take responsibility for the diffusion of innovation that is happening with AI right now. The wider the gap in society regarding AI competency, the more disparity and chaos will follow.
Interested people can give this book a read: Diffusion of Innovations by Everett Rogers.
https://t.co/zYWZgJ0iZx
The rate of progress in the labs is accelerating
The rate of adoption of that progress in society is not
It’s going to go both very fast on one end and it will feel slower than ever to those who understand AI because society has natural brakes
Fast takeoff with slow uptake
@Jason@XMoney I need $500 to get registered as apple developer and sign the product app that I built. To start selling my product at https://t.co/DGkeIMXFnL
This can single handedly make my product from beta testing with closed friends to up on website selling it within a month.
I was in that place a couple months ago, binded to one or other AI service provider and not owning my own context, memory and project data. Then I created a second brain wiki using obsidian. Now all my life data which I choose to expose to AI including all projects, context and memory lives in that wiki on my computer locally. And I am free to switch any AI service provider at any time without any consequences, more over I am using both Claude and ChatGPT on the same project turn by turn because data is mine and context is free to point towards for LLMs. Furthermore I can connect different project information or aspects of life which I might miss through the knowledge graph that exists in obsidian. This has been the best thing I have done for my workflow💯
Prompt Engineering is kinda dead; it has evolved into the skill of clear articulation, communication, and making sure you give all important info about and around the task you intend to get done. If your project's intent.md is precise and in line, everything else tends to fall into place as well.
I am surprised that people are surprised this is how I prompt Claude.
Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out.
Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model:
1. What you want it to do
2. How much effort you want it to spend
3. How it should verify that it did the right thing