Category profession
Vidable.ai
Vidable.ai was a startup I worked for. It was a platform that connected to video sources, and later websites and documents, to feed an AI system. The initial release focused...
Where the puck is going: An AI Roadmap
I created this AI roadmap last year for our internal team, and we’re somewhere around line 6.5 as of May 2024 (current video multimodal models are just looking at periodic...
Empowering blind instructors to control classroom technology
One of my more successful early projects was creating a way to allow blind users to control classroom technology. The implementation used features of Crestron panels in a clever way...
Category research
Bringing Photos to Life: Gaussian Splatting with Jiggle Physics in VisionOS
What if your photos could move? Not just play back as videos, but actually exist in space around you—touchable, interactive, alive with physics?
Hyperfast AI: Rethinking Design for 1000 tokens/s
I recently spoke at AI Tinkerers Raleigh about hyperfast inference systems and how they’re fundamentally changing AI application design. If you haven’t heard of Cerebras (or however they pronounce it),...
Why you may not have to worry about superintelligent AI as much: Entropy
The Simple Reason You Don’t Have to Worry About Super Intelligent AI: Entropy
LLM Visualization: How embedding space creates intelligence
Using Python I created this visualization to help explain how LLMs capture and synthesize information. LLMs take the encoding of language and deconstruct it into concepts.
Where the puck is going: An AI Roadmap
I created this AI roadmap last year for our internal team, and we’re somewhere around line 6.5 as of May 2024 (current video multimodal models are just looking at periodic...
EleutherAI: Tool Use Idea
I created a working diagram of how a set of agent AI models could be used to answer math questions using tools. At the time I wrote this post, tool...
SwiftUI Mars App
As an aficionado of the Mars Rover missions, I decided to create a simple app that would allow me to view the latest images from the Mars Rover missions. I...
Empowering blind instructors to control classroom technology
One of my more successful early projects was creating a way to allow blind users to control classroom technology. The implementation used features of Crestron panels in a clever way...
Category contalk
ConTalk: Apple's On-Device VLM: The Future of Multimodal AI
When we think about the future of artificial intelligence, we often imagine systems that can think like humans—not just processing text, but understanding images, video, and even the physical properties...
Empowering blind instructors to control classroom technology
One of my more successful early projects was creating a way to allow blind users to control classroom technology. The implementation used features of Crestron panels in a clever way...
Category youtube
ConTalk: Apple's On-Device VLM: The Future of Multimodal AI
When we think about the future of artificial intelligence, we often imagine systems that can think like humans—not just processing text, but understanding images, video, and even the physical properties...
Cerebras OS - OpenRouter Hackathon Project
When AI becomes fast enough, computing itself changes. Cerebras OS is a hackathon project exploring what happens when inference speed crosses a threshold—when AI stops being something you wait for...
Cohere AI: LLM Hackathon #3 3rd place winner
I participated practically solo in the CoHere AI Hackathon to use an early version of the Cohere LLM to make an app. The project came in third out of thousands...
Empowering blind instructors to control classroom technology
One of my more successful early projects was creating a way to allow blind users to control classroom technology. The implementation used features of Crestron panels in a clever way...
Category accessibility
Empowering blind instructors to control classroom technology
One of my more successful early projects was creating a way to allow blind users to control classroom technology. The implementation used features of Crestron panels in a clever way...
Category hobby
MIDI Poly-Sequencer Synth
Inspired by instagram videos of a user playing a “stylophone” i wanted to see if i could replicate this on an iPhone. There are many tools that could possibly be...
ConTalk: Apple's On-Device VLM: The Future of Multimodal AI
When we think about the future of artificial intelligence, we often imagine systems that can think like humans—not just processing text, but understanding images, video, and even the physical properties...
Cerebras OS - OpenRouter Hackathon Project
When AI becomes fast enough, computing itself changes. Cerebras OS is a hackathon project exploring what happens when inference speed crosses a threshold—when AI stops being something you wait for...
Apple Intelligence features for any iPhone
Apple prides itself on safety and privacy, but if you’re willing to sacrifice some of that, and you have an older iPhone, you can use the Shortcuts app to create...
Apple Vision Pro Music Viz App
Currently a WIP, but using audio processing APIs and particle emitter SDK, i’m working on a music visualizer app to be completely immersed in a 3D field of dancing particles....
Why you may not have to worry about superintelligent AI as much: Entropy
The Simple Reason You Don’t Have to Worry About Super Intelligent AI: Entropy
LLM Visualization: How embedding space creates intelligence
Using Python I created this visualization to help explain how LLMs capture and synthesize information. LLMs take the encoding of language and deconstruct it into concepts.
LessWrong: ChatGPT is our Wright Brothers Moment
There’s a lot of discussions, often derisively, that many AI apps are “just” ChatGPT wrappers. I wrote a short article that was promoted to the front page of LessWrong about...
Cohere AI: LLM Hackathon #3 3rd place winner
I participated practically solo in the CoHere AI Hackathon to use an early version of the Cohere LLM to make an app. The project came in third out of thousands...
EleutherAI: Tool Use Idea
I created a working diagram of how a set of agent AI models could be used to answer math questions using tools. At the time I wrote this post, tool...
SwiftUI Mars App
As an aficionado of the Mars Rover missions, I decided to create a simple app that would allow me to view the latest images from the Mars Rover missions. I...
Category mars
SwiftUI Mars App
As an aficionado of the Mars Rover missions, I decided to create a simple app that would allow me to view the latest images from the Mars Rover missions. I...
Category swift
Apple Vision Pro Music Viz App
Currently a WIP, but using audio processing APIs and particle emitter SDK, i’m working on a music visualizer app to be completely immersed in a 3D field of dancing particles....
SwiftUI Mars App
As an aficionado of the Mars Rover missions, I decided to create a simple app that would allow me to view the latest images from the Mars Rover missions. I...
Category xcode
Apple Vision Pro Music Viz App
Currently a WIP, but using audio processing APIs and particle emitter SDK, i’m working on a music visualizer app to be completely immersed in a 3D field of dancing particles....
SwiftUI Mars App
As an aficionado of the Mars Rover missions, I decided to create a simple app that would allow me to view the latest images from the Mars Rover missions. I...
Category AI
Bringing Photos to Life: Gaussian Splatting with Jiggle Physics in VisionOS
What if your photos could move? Not just play back as videos, but actually exist in space around you—touchable, interactive, alive with physics?
Hyperfast AI: Rethinking Design for 1000 tokens/s
I recently spoke at AI Tinkerers Raleigh about hyperfast inference systems and how they’re fundamentally changing AI application design. If you haven’t heard of Cerebras (or however they pronounce it),...
ConTalk: Apple's On-Device VLM: The Future of Multimodal AI
When we think about the future of artificial intelligence, we often imagine systems that can think like humans—not just processing text, but understanding images, video, and even the physical properties...
Cerebras OS - OpenRouter Hackathon Project
When AI becomes fast enough, computing itself changes. Cerebras OS is a hackathon project exploring what happens when inference speed crosses a threshold—when AI stops being something you wait for...
Apple Intelligence features for any iPhone
Apple prides itself on safety and privacy, but if you’re willing to sacrifice some of that, and you have an older iPhone, you can use the Shortcuts app to create...
Vidable.ai
Vidable.ai was a startup I worked for. It was a platform that connected to video sources, and later websites and documents, to feed an AI system. The initial release focused...
Why you may not have to worry about superintelligent AI as much: Entropy
The Simple Reason You Don’t Have to Worry About Super Intelligent AI: Entropy
LLM Visualization: How embedding space creates intelligence
Using Python I created this visualization to help explain how LLMs capture and synthesize information. LLMs take the encoding of language and deconstruct it into concepts.
Where the puck is going: An AI Roadmap
I created this AI roadmap last year for our internal team, and we’re somewhere around line 6.5 as of May 2024 (current video multimodal models are just looking at periodic...
LessWrong: ChatGPT is our Wright Brothers Moment
There’s a lot of discussions, often derisively, that many AI apps are “just” ChatGPT wrappers. I wrote a short article that was promoted to the front page of LessWrong about...
Cohere AI: LLM Hackathon #3 3rd place winner
I participated practically solo in the CoHere AI Hackathon to use an early version of the Cohere LLM to make an app. The project came in third out of thousands...
EleutherAI: Tool Use Idea
I created a working diagram of how a set of agent AI models could be used to answer math questions using tools. At the time I wrote this post, tool...
SwiftUI Mars App
As an aficionado of the Mars Rover missions, I decided to create a simple app that would allow me to view the latest images from the Mars Rover missions. I...
Category imageprocessing
SwiftUI Mars App
As an aficionado of the Mars Rover missions, I decided to create a simple app that would allow me to view the latest images from the Mars Rover missions. I...
Category hackathon
Cerebras OS - OpenRouter Hackathon Project
When AI becomes fast enough, computing itself changes. Cerebras OS is a hackathon project exploring what happens when inference speed crosses a threshold—when AI stops being something you wait for...
Cohere AI: LLM Hackathon #3 3rd place winner
I participated practically solo in the CoHere AI Hackathon to use an early version of the Cohere LLM to make an app. The project came in third out of thousands...
Category AWS
Cohere AI: LLM Hackathon #3 3rd place winner
I participated practically solo in the CoHere AI Hackathon to use an early version of the Cohere LLM to make an app. The project came in third out of thousands...
Category serverless
Cohere AI: LLM Hackathon #3 3rd place winner
I participated practically solo in the CoHere AI Hackathon to use an early version of the Cohere LLM to make an app. The project came in third out of thousands...
Category github
Cerebras OS - OpenRouter Hackathon Project
When AI becomes fast enough, computing itself changes. Cerebras OS is a hackathon project exploring what happens when inference speed crosses a threshold—when AI stops being something you wait for...
Cohere AI: LLM Hackathon #3 3rd place winner
I participated practically solo in the CoHere AI Hackathon to use an early version of the Cohere LLM to make an app. The project came in third out of thousands...
Category writing
Game Storyizer
I’ve built a new tool called Game Storyizer. It’s a node-based narrative builder designed to help game developers and writers create complex, branching storylines.
Why you may not have to worry about superintelligent AI as much: Entropy
The Simple Reason You Don’t Have to Worry About Super Intelligent AI: Entropy
LessWrong: ChatGPT is our Wright Brothers Moment
There’s a lot of discussions, often derisively, that many AI apps are “just” ChatGPT wrappers. I wrote a short article that was promoted to the front page of LessWrong about...
Category python
LLM Visualization: How embedding space creates intelligence
Using Python I created this visualization to help explain how LLMs capture and synthesize information. LLMs take the encoding of language and deconstruct it into concepts.
Category visualization
LLM Visualization: How embedding space creates intelligence
Using Python I created this visualization to help explain how LLMs capture and synthesize information. LLMs take the encoding of language and deconstruct it into concepts.
Category alignment
Why you may not have to worry about superintelligent AI as much: Entropy
The Simple Reason You Don’t Have to Worry About Super Intelligent AI: Entropy
Category music
MIDI Poly-Sequencer Synth
Inspired by instagram videos of a user playing a “stylophone” i wanted to see if i could replicate this on an iPhone. There are many tools that could possibly be...
Apple Vision Pro Music Viz App
Currently a WIP, but using audio processing APIs and particle emitter SDK, i’m working on a music visualizer app to be completely immersed in a 3D field of dancing particles....
Category visionpro
Apple Vision Pro Music Viz App
Currently a WIP, but using audio processing APIs and particle emitter SDK, i’m working on a music visualizer app to be completely immersed in a 3D field of dancing particles....
Category terraform
Vidable.ai
Vidable.ai was a startup I worked for. It was a platform that connected to video sources, and later websites and documents, to feed an AI system. The initial release focused...
Category devops
Vidable.ai
Vidable.ai was a startup I worked for. It was a platform that connected to video sources, and later websites and documents, to feed an AI system. The initial release focused...
Category microservices
Vidable.ai
Vidable.ai was a startup I worked for. It was a platform that connected to video sources, and later websites and documents, to feed an AI system. The initial release focused...
Category docker
Vidable.ai
Vidable.ai was a startup I worked for. It was a platform that connected to video sources, and later websites and documents, to feed an AI system. The initial release focused...
Category iOS
ConTalk: Apple's On-Device VLM: The Future of Multimodal AI
When we think about the future of artificial intelligence, we often imagine systems that can think like humans—not just processing text, but understanding images, video, and even the physical properties...
Apple Intelligence features for any iPhone
Apple prides itself on safety and privacy, but if you’re willing to sacrifice some of that, and you have an older iPhone, you can use the Shortcuts app to create...
Category tutorial
Apple Intelligence features for any iPhone
Apple prides itself on safety and privacy, but if you’re willing to sacrifice some of that, and you have an older iPhone, you can use the Shortcuts app to create...
Category react
MIDI Poly-Sequencer Synth
Inspired by instagram videos of a user playing a “stylophone” i wanted to see if i could replicate this on an iPhone. There are many tools that could possibly be...
Category interactive
MIDI Poly-Sequencer Synth
Inspired by instagram videos of a user playing a “stylophone” i wanted to see if i could replicate this on an iPhone. There are many tools that could possibly be...
Category gamedev
Paint Mix Simulator: A Colorful Chaos
I’m delighted to introduce Paint Mix Simulator, a delightfully chaotic little minigame where you get to play with colors… and face the wrath of Gordon Ramsay.
Midnight City Sailing
I’m excited to share a new experimental project: Midnight City Sailing. It’s a serene, atmospheric sailing experience set in a procedurally-generated neo-gothic cityscape.
Nate the Hoof Guy Simulator
I’m excited to share a new fan-made project: Nate the Hoof Guy Simulator. It’s a web-based simulation game inspired by the oddly satisfying videos of bovine hoof trimming.
Game Storyizer
I’ve built a new tool called Game Storyizer. It’s a node-based narrative builder designed to help game developers and writers create complex, branching storylines.
Find Your Jacket: A Winter Puzzle
I’m excited to share a new mini-game: Find Your Jacket. It’s a short, atmospheric puzzle game set in a frozen cabin.
Category puzzle
Find Your Jacket: A Winter Puzzle
I’m excited to share a new mini-game: Find Your Jacket. It’s a short, atmospheric puzzle game set in a frozen cabin.
Category webgl
Paint Mix Simulator: A Colorful Chaos
I’m delighted to introduce Paint Mix Simulator, a delightfully chaotic little minigame where you get to play with colors… and face the wrath of Gordon Ramsay.
Midnight City Sailing
I’m excited to share a new experimental project: Midnight City Sailing. It’s a serene, atmospheric sailing experience set in a procedurally-generated neo-gothic cityscape.
Nate the Hoof Guy Simulator
I’m excited to share a new fan-made project: Nate the Hoof Guy Simulator. It’s a web-based simulation game inspired by the oddly satisfying videos of bovine hoof trimming.
Find Your Jacket: A Winter Puzzle
I’m excited to share a new mini-game: Find Your Jacket. It’s a short, atmospheric puzzle game set in a frozen cabin.
Category tool
FastRecord: Screen Recording Made Simple
I’m happy to introduce FastRecord, a new lightweight screen recording tool I’ve been working on. Everything runs locally on your device, with no data sent to the cloud.
Game Storyizer
I’ve built a new tool called Game Storyizer. It’s a node-based narrative builder designed to help game developers and writers create complex, branching storylines.
Category simulation
Paint Mix Simulator: A Colorful Chaos
I’m delighted to introduce Paint Mix Simulator, a delightfully chaotic little minigame where you get to play with colors… and face the wrath of Gordon Ramsay.
Nate the Hoof Guy Simulator
I’m excited to share a new fan-made project: Nate the Hoof Guy Simulator. It’s a web-based simulation game inspired by the oddly satisfying videos of bovine hoof trimming.
Category oddlysatisfying
Nate the Hoof Guy Simulator
I’m excited to share a new fan-made project: Nate the Hoof Guy Simulator. It’s a web-based simulation game inspired by the oddly satisfying videos of bovine hoof trimming.
Category talk
Hyperfast AI: Rethinking Design for 1000 tokens/s
I recently spoke at AI Tinkerers Raleigh about hyperfast inference systems and how they’re fundamentally changing AI application design. If you haven’t heard of Cerebras (or however they pronounce it),...
Category UX
Hyperfast AI: Rethinking Design for 1000 tokens/s
I recently spoke at AI Tinkerers Raleigh about hyperfast inference systems and how they’re fundamentally changing AI application design. If you haven’t heard of Cerebras (or however they pronounce it),...
Category sailing
Midnight City Sailing
I’m excited to share a new experimental project: Midnight City Sailing. It’s a serene, atmospheric sailing experience set in a procedurally-generated neo-gothic cityscape.
Category atmospheric
Midnight City Sailing
I’m excited to share a new experimental project: Midnight City Sailing. It’s a serene, atmospheric sailing experience set in a procedurally-generated neo-gothic cityscape.
Category audio
FastRecord: Screen Recording Made Simple
I’m happy to introduce FastRecord, a new lightweight screen recording tool I’ve been working on. Everything runs locally on your device, with no data sent to the cloud.
Category webapp
FastRecord: Screen Recording Made Simple
I’m happy to introduce FastRecord, a new lightweight screen recording tool I’ve been working on. Everything runs locally on your device, with no data sent to the cloud.
Category fun
Paint Mix Simulator: A Colorful Chaos
I’m delighted to introduce Paint Mix Simulator, a delightfully chaotic little minigame where you get to play with colors… and face the wrath of Gordon Ramsay.
Category VisionOS
Bringing Photos to Life: Gaussian Splatting with Jiggle Physics in VisionOS
What if your photos could move? Not just play back as videos, but actually exist in space around you—touchable, interactive, alive with physics?
Category AR
Bringing Photos to Life: Gaussian Splatting with Jiggle Physics in VisionOS
What if your photos could move? Not just play back as videos, but actually exist in space around you—touchable, interactive, alive with physics?
Category computer-vision
Want to work with me? Send me an email.