The Web3 Disciple

@_lamaahmad @Miles_Brundage Exciting initiative! Note that there is an error in the current form for LinkedIn link (last question)

I'm so fortunate to be able to lead this work at OpenAI - and my priority is increasing the diversity in domains, geographies, language representation, and lived experiences of those who we invite to test our systems and shape our mitigations. Please apply!

I bet I'm not the only one that has convos like this: Me: LLMs are generational tech. I'm excited and terrified. Them: You're worried about a Terminator / Kurzweil scenario? Me: A bit. I'm more worried about chaos in the next 2-5 years. Them: What exactly do you mean?

@mckaywrigley Resolved: did some careful copy-pasting from your json file (folder and prompt structure) into an export of my data, then re-uploaded. Time to dig in!

@mckaywrigley Thanks for all your amazing work on this! Do you know of any ways to preserve my history (and current set of prompts) when importing your prompt cheat sheet?

V1 of my prompt cheatsheet is live! Download the json file and import it into Chatbot UI to add 20+ prompts to your code workflow. I’ll be back soon with: - More complex, powerful prompts. - A system for choosing which prompts you want to use. GitHub: github.com/mckaywrigley/p…

@TheSeaMouse Thanks for your helpful reply! Looking forward to trying this out and comparing differences with those tricks you mention

@Web3Disciple Same process, just more chunks. Vector DBs scale easily to millions of documents and query times are in the ms to fractions of ms times. One trick you can do to help is add the title of the document or a summary of the PDF to each chunk. But that's optional

Simple 4-part explainer on how to query a PDF (or a set of PDFs) using GPT-3

@stewfortier Been using multiple. Definitely interested!

Paging my fellow AI content nerds – if you've ever paid for a product like Jasper or CopyAI, send me a DM. I want to give you early access to a new thing.

If you ever notice someone become more alive when they speak, point it out to them. There's a good chance the other person needs to spend more time reflecting on that moment. All kinds of clarity can follow.

As the year is coming to an end, let's take the time to highlight many of the amazing community contributions and projects over the year... Stable Diffusion has only been around for 6 months but a full thread is still warranted given the extremely fast pace of progress! ↓

someone wants to read what you have to say

To be clear, calm and focused: 1) Sleep well and enough (for you). 2) If you didn’t sleep well, don’t externalize your thoughts any more than absolutely necessary until after you do.

confidence in your craft is necessary, ppl can feel when you have conviction in your work and you’d be surprised how much it affects how they view it. Be proud of who you are and what you make.

It’s not 10,000 hours, it’s 10,000 iterations.

You will never live if you are looking for the meaning of life. Fall in love with some activity and do it! Nobody ever figures out what life is all about and it doesn't matter.

I recently came across data on who we spend our time with over the course of our lives. The insights are simultaneously inspiring and depressing. Here are 6 graphs everyone needs to see:

most of the world has lost the will to do big things--incredible alpha now in working on a big project. most of the world has also lost the ability to think on a long time horizon. combine the two and you'll be really happy!

What happens when you ask an AI to generate "Human Evolution." This is terrifying.

Introducing the @sequoia Gen AI Market Map!🌎 We’ve decided to map out this emerging frontier, thanks to all the contributions and feedback we’ve received. This space is moving quickly – this map is a living document, so keep the suggestions coming! Who else should we include?

Tsundoku: a Japanese term for the phenomenon of acquiring reading materials but letting them pile up in one's home without reading them. So happy I have now a term for this major issue in my life. Here's a small part of my current tsundoku pile. What's in yours?

@emollick How do you consistently find such a wide and interesting range of scientific studies?

It is kind of freaky to think that over 8% of our genome is just fossilized virus DNA that once invaded our ancestors’ DNA and that we now endlessly reproduce. And stranger: extinct viruses have been reconstructed from our DNA. They were still infectious! sciencedaily.com/releases/2006/…