AI cannot develop software for you, but that's not going to stop people from trying to make it happen anyway. And that is going to turn all of the easy software development problems into hard problems.

• A computer can never be held accountable. Therefore, a computer must never make a management decision.

Programming as Theory Building

Non-trivial software changes over time. The requirements evolve, flaws need to be corrected, the world itself changes and violates assumptions we made in the past, or it just takes longer than one working session to finish. And all the while, that software is running in the real world. All of the design choices taken and not taken throughout development; all of the tradeoffs; all of the assumptions; all of the expected and unexpected situations the software encounters form a hugely complex system that includes both the software itself and the people building it. And that system is continuously changing.

To circle back to AI like ChatGPT, recall what it actually does and doesn't do. It doesn't know things. It doesn't learn, or understand, or reason about things. What it does is probabilistically generate text in response to a prompt.

A great deal of my learnings and inspiration comes from the great content from Yubin Ma at AiTuts, where you can learn more about prompting and view a myriad of examples.

I've watched the 4 videos from 3blue1brown on neural nets. The web and youtube are awash with mediocre videos on Large Language Models. I'm looking for a good one.

This is part of a longer series but is maybe the single best video I know of on the topic:
https://youtu.be/kCc8FmEb1nY?si=zmBleKwlpV06O3Mw

I thought this video from Steven Wolfram was also quite good:
https://www.youtube.com/live/flXrLGPY3SU?si=SrP1EJFMPJqVCFPL

A deep-dive into machine learning embeddings.

Covering the state of play as of Summer, 2023

This is a gentle introduction to how Stable Diffusion works.

People often ask me how to use AI. Here's an overview with lots of links.

• The Six Large Language Models
• Write stuff
• Make Images
• Come up with ideas
• Make videos
• Coding

Yes, there has been much hype over the imagined powers and flaws of the new Large Language Models (e.g., Chat GPT-4), but the recent advances (that is, as of today in April 2023) indicate that ther…

https://arxiv.org/pdf/2303.12712.pdf

A talk by the lead author, Sebastian Bubeck, at MIT on March 22, 2023: Sparks of AGI: Early experiments with GPT-4.
https://www.youtube.com/watch?v=qbIk7-JPB2c

Stephen Wolfram explores the broader picture of what's going on inside ChatGPT and why it produces meaningful text. Discusses models, training neural nets, embeddings, tokens, transformers, language syntax.

Research means more than fact-checking

When I first used GitHub Copilot, I said it “essen­tially tasks you with correcting a 12-year-old’s home­work … I have no idea how this is prefer­able to just doing the home­work your­self.” What I meant is that often, the focus of program­ming is not merely producing code that solves a problem. Rather, the code tends to be the side effect of a deeper process, which is to learn and under­stand enough about the problem to write the code. The authors of the famous MIT program­ming text­book Struc­ture and Inter­pre­ta­tion of Computer Programs call this virtuous cycle proce­dural epis­te­mology. We could also call it by its less exotic name: research.

Also:

https://bootcamp.uxdesign.cc/20-incredible-midjourney-prompts-that-will-blow-your-mind-part-2-463ae919b6c3

The short answer is that they convert documents that are over 100 or even 1,000 pages long into a numeric representation of data and related context (vector embedding) and store them in a vector search engine.

https://betterprogramming.pub/how-to-build-your-own-custom-chatgpt-with-custom-knowledge-base-4e61ad82427e

2. Extending ChatGPT With LlamaIndex (GPT Index)
   LlamaIndex, also known as the GPT Index, is a project that provides a central interface to connect your LLMs with external data. Yeah, you read that correctly. With LlamaIndex, we can build something that looks like the illustration below:

https://levelup.gitconnected.com/its-time-to-create-a-private-chatgpt-for-yourself-today-6503649e7bb6

🧠 Memory Bot 🤖 — An easy up-to-date implementation of ChatGPT API, the GPT-3.5-Turbo model, with LangChain AI's 🦜 — ConversationChain memory module with Streamlit front-end. With the emergence of…

https://github.com/avrabyt

Amazing Lighting Effects Introduced In MidJourney V5. “How To Master Lighting In Midjourney V5” is published by Paul DelSignore in The Generator.

How to Create a Style or Character in Midjourney, That you can Then Prompt with a Single Word.. A hack you won’t find in the official documentation.

Looking for a free and easy way to come up with catchy titles for your content? Try our free catchy title generator tool! Our tool uses AI and natural language processing to generate unique and engaging titles for your blog posts, articles, social media posts, and more. With our tool, you can save time and boost your content's visibility and engagement. Try it now and see the difference it can make for your content marketing strategy!

Prompt: Let's create an icon set for design patterns. Here are the parameters for building individual icons in the icon set

• the icon will be used on a website and even in an app
• the icon needs to be square in shape
• the icon needs to represent the design pattern in context
• Use a minimalist design style
• use stroke size as 1 for all lines
• use complementary colours; probably pastel colour shades
• use colours in a way that they can be adapted to the entire set
• define a consistent and uniform style that we can propagate to other icons in the set
  I need you to create this icon in SVG format and provide the SVG code for the icon

https://github.com/aruva-xyz/svg-icons-by-chatgpt.git

The authors of Stable Diffusion, a latent text-to-image diffusion model, have released the weights of the model and it runs quite easily and cheaply on standard GPUs. This article shows you how you can generate images for pennies (it costs about 65c to generate 30–50 images).

• Stay away from unsupervised learning
• Skip neural networks
  Plugging an on off-the-shelf model from sklearn is often enough for an MVP. While weeks of tuning a neural net might provide a couple extra points of f1, it’s often not worth it in the beginning.
• Frame all problems as binary classification
• Tune your hyper-parameters