I was expecting him to read a proper prompt. The prompt would be what he would tell the AI system.
“You are a speech writer, an expert on XYZ… your task is to write ABC…”
It’s not too bad, at least he is using ai. And agree we can replace many of them with AI. At least we will have the opportunity to talk to the ai directly about concerns.
One very tiny silver lining in all this will be leaked prompts. E.g. we all know how a non-apology reads, and call them out as such already, but when you see "write a really contrite apology without actually conceding anything while subtly casting doubt on the character of those making the accusations, but in a way that seems really open and constructive" it'll hit different still, I think.
Wrote a short article about my state management journey in React. The tl;dr; is 10 years of react, I decided to keep things simple and only `useState` and basic react hooks.
For the last 3 years, I've been using basic react hooks and it was more than enough. Until, I tried to build a more complex UI and finally needed a bit more.
Endedup using Zustand to help manage the state and avoid stale inter-connected state.
A few makers like myself got a message this morning from OpenAI warning us about access from unsupported regions. It was cryptic and confusing.
We suspect it has to do with Edge function being used on Vercel which in turn uses Cloudflare. Thus, Vercel and cloudflare customers might be affected.
Totally fair, and I was really excited about the iOS safari built-in version. It didn't work for the book I bought and then after using AI bases TSS, I just couldn't go back.
I would love to be able to run the models on the device, and it will come in the future. The OSS models are not quite there from a quality standpoint yet. But they will surly get there
I was expecting him to read a proper prompt. The prompt would be what he would tell the AI system.
“You are a speech writer, an expert on XYZ… your task is to write ABC…”
It’s not too bad, at least he is using ai. And agree we can replace many of them with AI. At least we will have the opportunity to talk to the ai directly about concerns.