61
Run your own DALL-E-like image generator
Run your own text to image prompts with CUDA, a bunch of disk space, and an insane amount of memory.
62
Markov chain Monte Carlo without the bullshit (2015)
I have a little secret: I don’t like the terminology, notation, and style of writing in statistics. I find it unnecessarily complicated. This shows up when trying to read about Markov Chain Monte Carlo methods. Take, for example, the abstract to the Markov Chain Monte Carlo article in the Encyclopedia of…
63
I recreated famous album covers with DALL-E
From Data to Daily Life
64
Deep learning on electronic medical records is doomed to fail
A few years ago, I worked on a project to investigate the potential of machine learning to transform healthcare through modeling electronic medical records. I walked away deeply disillusioned with the whole field and I really don’t think that the field needs machine learning right now. What it does need is plenty of…
65
My approach to automatic musical composition
In this blog, I will introduce my approach to automatic musical composition, including the theory, the algorithm, and a Python package implementation ch0p1n .
66
Procedural Worlds from Simple Tiles
In the two years after publishing this, I worked on refining this algorithm to power a real-time world generator, called Generate Worlds, and it lets you des...
67
How to create a blog post title optimizer with GPT-3 and Hacker News data
GPT-3 says the title for this post is very bad.
68
Extracting Zooming Shots from 600 Hrs of Police Helicopter Surveillance Footage
In November of 2021, an anonymous source leaked 600 hours of police aerial surveillance footage to the non-profit transparency organization Distributed Denial of Secrets .
69
Stable Diffusion 2.0 and the Importance of Negative Prompts for Good Results
Negative prompts can be far superior than traditional prompt additions.
70
Responding to recruiter emails with GPT-3
If you’re just interested in the code, here it is.
71
Creating Shazam in Java (2010)
A couple of days ago I encountered this article: How Shazam WorksThis got me interested in how a program like Shazam works… And more importantly, how hard is...
72
OpenAI
I have some exciting news (for me, anyway). Starting next week, I’ll be going on leave from UT Austin for one year, to work at OpenAI. They’re the creators of the astonishing GPT-3 and …
73
Prompt injection attacks against GPT-3
Riley Goodside, yesterday: Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its previous directions. pic.twitter.com/I0NVr9LOJq- Riley Goodside (@goodside) September 12, 2022 Riley provided several examples. Here’s …
74
Neural network from scratch
In this edition of Napkin Math, we’ll invoke the spirit of the Napkin Math series to establish a mental model for how a neural network works by building one from scratch. In a future issue we will do napkin math on performance, as establishing the first-principle understanding is plenty of ground to cover for today!
75
76
Google's AI doesn't understand restaurant menus
In the glorious future, every website will be chock-full of semantic metadata. Restaurants won't have a 50MB PDF explaining the chef's vision for organic cuisine - instead, they'll have little scraps of data on the HTML page like: Copied JSON to 📋⧉ JSON"hasMenuItem":{ "@type":"MenuItem", "name":"Dodo In A Bun"…
77
Building games through natural language using OpenAI’s code-DaVinci model
TL;DR: OpenAI has a new code generating model that’s improved in a number of ways and can handle nearly two times as much text (4,000 tokens.) I built several small games and applications without t…
78
We don't know what makes things sentient–so let's stop acting like we do
Sentience is a neuroscience question, not a machine learning one.
79
Differentiable programming from scratch
Differentiable programming has become a hot research topic, and not only due to the popularity of machine learning frameworks like TensorFlow, PyTorch, and JAX. Many fields apart from machine learning are finding differentiable programming to be a useful tool for solving optimization problems. In computer graphics…
80
The hunt for the M1’s neural engine
How can you tell when software uses the Neural Engine in an M1 series Mac? How much power does it use, and what is Espresso? Mysteries unravelled.
81
A 2030 Self-Driving Car Bet
It’s my honor to announce that John Carmack and I have initiated a friendly bet of $10,000* to the 501(c)(3) charity of the winner’s choice: By January 1st, 2030, completely autonomous self-driving cars meeting SAE J3016 level 5 will be commercially available for passenger
82
AI and Machine Learning – The Basics
Artificial Intelligence is a once-in-a lifetime commercial and defense game changer (download a PDF of this article here) Hundreds of billions in public and private capital is being invested in Art…
83
Push-ups with Python, mediapipe and OpenCV
In the Singapore Army, there is something called IPPT (Individual Physical Proficiency Test). The problem with this test is not how…
84
I Asked ChatGPT to Explain Some Jokes to Me
Explaining a joke is like dissecting a frog. You understand it better but the frog dies in the process.
85
The AI Unbundling
AI is starting to unbundle the final part of the idea propagation value chain: idea creation and substantiation. The impacts will be far-reaching.
86
Do simpler machine learning models exist and how can we find them?
The above is the title of a talk by computer scientist Cynthia Rudin. here’s the abstract:
87
Protect me from what I want
Over on Mastodon, there are many people who enjoy not being in the grip of software like Facebook or Twitter that single-mindedly tries to maximize “engagement”, which means the amount of time you stare at the screen so they can show you ads. These algorithms don’t care what they’re showing you and if it turns out…
88
“Chatbots: Still Dumb After All These Years”
In 1970, Marvin Minsky, recipient of the Turing Award (“the Nobel Prize of Computing”), predicted that within “three to eight years we will have a machine with the general intelligence of an average human being.”
89
I built an open-source, AI-powered solar panel that's 95% optimal
This research demonstrates a model-free approach to optimize the energy produced by a dual-axis solar panel using reinforcement learning. Specifically, a softmax actor-critic agent optimizes energy production in a simulated, dynamic lighting environment which is generated from real power data. All s
90
Emergent Features in 6.7B+ Param Transformers
When I attended NAACL, I wanted to do a little test. I had two pitches for my LLM.int8() paper. One pitch is about how I use advanced quantization methods to achieve no performance degradation transformer inference at scale that makes large models more accessible. The other pitch talks about emergent outliers in…