Exploring the Cutting Edge: Key Trends in the LLM and Generative AI Developer Community

July 27, 2023 3 minutes 2 photos

Key trends shaping practical LLM development today: democratizing AI with Skyglass, LEDITS, and lean tools; automating workflows (Watto AI, Autonomous Finance); customizing experiences (ai-jsx, Talk to Merlin); multimodal and knowledge-synthesis (Decoupage, System Pro); and responsible AI (Privacy.ai, BlindBox), while tackling data, infra, and prompt-engineering challenges.

Read post

Architecture Maestro from Now On

March 22, 2023 3 minutes

Architectural maestro mode with GPT-4: I fed 20-year NAS Ruby scripts (rsync + Glacier) and asked to extract EXIF, reverse geocode, and index data per folder. GPT-4 rewrote, added gems, fixed version issue, parallelized IO, added a progress bar and mutex handling; it ran in ~30s and saved a day.

Read post

About Calorie Coach

January 01, 2023 2 minutes 2 photos

Calorie Coach is an AI-powered calorie tracker you use via SMS at 325-225-6743 (325-CALORIE) or caloriecoach.ai. It asks your age, gender, weight, and goals to tailor daily needs and track progress; just text a quick food description and you’ll get meal-time reminders. Ask for help for a reminder URL.

Read post

Launching DREAM.page

November 10, 2022 1 minute

Today I launched DREAM.page, an AI-first personal publishing platform, and I’m excited to see how the community uses it in these early days. Check out the video walk-through, sign up here, and DM me to move from the wait list into the actual product.

Read post

AI assisted blog images

October 23, 2022 2 minutes 4 photos

AI-assisted blog images: Boris Johnson pulls out of Britain's leadership race, saying he has enough MPs to advance but far fewer than frontrunner Rishi Sunak. Our process uses GPT-3 and Stable Diffusion to render a distant, long-lens image of a suited man before the Houses of Parliament.

Read post

My first deep learning model: Doo Doo Detective

September 26, 2022 3 minutes 2 photos

I built and deployed end-to-end DL image recognizer to detect when Kona is doing her business. Using FastAI, I fine-tuned ResNet-18 on 100s of images, tested with a confusion matrix, iterated, and launched a Gradio app on Hugging Face in ~2 hours. DALL-E 2 for dog-poop data is blocked.

Read post

Stable Diffusion Test

September 08, 2022 1 minute 4 photos

Want to add photos to a post? Use the blogging software I’ve long wanted: select the description and click 'stable diffusion' to auto-insert a stable-diffusion tag and handle it for you. Example: photo of a puppy jumping through a muddy pond, nikon d50, 100mm, bokeh. Awesome results—thanks, rainbow tag.

Read post

Zoom meeting backgrounds (DALL·E 2)

August 01, 2022 1 minute 67 photos

Upgrade your next Zoom with personality using DALL·E 2 AI-generated backgrounds. Explore a wide range of options and you’re sure to find the perfect background to make your meeting stand out.

Read post

Let's test some photo frame renders!

July 17, 2022 3 minutes 15 photos

Sharing early blog tooling: auto handwriting via <handwriting> tags and photoreal framed image previews via <photorealpreview style='wood-frame-landscape'>; automatic portrait/landscape handling. Also demoing Octopress + Disqus, a Ruby-like processor, a 'Test Render' with iPhone 13 Pro, and DALL-E 2 generated visuals; AI writing tools coming.

Read post

More DALL·E 2 Generations

July 05, 2022 3 minutes 36 photos

Exploring DALL·E 2 generations: from a Leica M11 “Ultimate Question” to a glittery Bald Eagle in Audubon style, dog variations, and high-quality 2D pixel art prompts. Expect surprising results—sad clown portraits, Mao/space shuttle, NYC ice age, Venice pursuit, flying saucers, glowing aliens, and robot–human collaborations; wrappers added later.

Read post

DALL·E 2 Generations in the style of Banksy

July 05, 2022 3 minutes 8 photos

Here's Ed’s Banksy-style prompts for DALL·E 2: 'New graffiti by Banksy,' 'Anti-environmentalism' and 'Pro-consumerism' in Banksy style, plus 'Political campaign poster for Joe Biden' and 'New McDonalds logo designed by Banksy' (Ronald skeleton). GPT-3 refined prompts like 'Pro-consumerism ... bright colors' and 'Anti-environmentalism ... destruction of nature.'

Read post

My first experiments with DALL·E

July 02, 2022 7 minutes 67 photos

I’ve just gained access to DALL·E 2 and here are my first generations: two mummies sipping espresso in Italy (50mm lens, high-quality photo) and a lemon gelato heart in a cobblestone Italian courtyard, plus Banksy-stenciled Bernedoodles, Dali-inspired scenes, and more.

Read post

Open AI / GPT-3 Presentation

February 24, 2022 22 minutes

GPT-3 is OpenAI’s 175‑billion‑parameter deep‑learning language model (trained on ~570 GB of text) you access via a simple prompt-based API; it runs on a massive 10,000‑GPU supercomputer, with a 350 GB model, Davinci at $0.060/1K tokens, 50–500 ms latency, and prompts that shape outputs—context is king.

Read post

Projects

June 07, 2020 3 minutes 11 photos

Explore my AI tinkering hub—Seattle’s AI Tinkerers and DREAM.page, plus practical tools like ReVision, Train for SDXL, AI Long Doc Summarizer, Sloppy Joe handwriting, arXiv Spotlight, and Commander (full self-driving for the internet).

Read post

“Please help me understand the value of working with a VC”

April 06, 2015 3 minutes

Value of VC: money, credibility, pattern-matching; most success comes from you, the team; two archetypes: A (growth, confident money-use) and B (need to prove risks), better to be A; good VCs provide patience, extra funding, intros, credibility; assess VCs by past ups/downs, key customers/hires; consider not raising money (C).

Read post

What are you passionate about in a company?

February 27, 2013 4 minutes 3 photos

Be on a purposeful mission, work with the best people, and build a beautiful, customer‑focused experience while breaking new ground—whether in product, design, or business model. A startup should test unproven hypotheses, but never privilege the model over market fit, customer acquisition, and operations.

Read post

Seattle Half Marathon Recap

November 25, 2012 2 minutes 4 photos

Seattle Half Marathon recap: foggy downtown, the I-90 tunnel felt like a treadmill with a megaphone cue for half-marathoners. Aid stations were everywhere—no water or GU needed. Madison–Interlaken hills were tough but doable; energy of runners carried us. Marching/bluegrass bands, Interlaken beauty, Krispy Kreme finish, and a baby announcement.

Read post

How to Print Your Own Children’s Books (that won’t be eaten or torn apart)

January 04, 2012 3 minutes

Turn baby photos into durable board books with three options: My Custom Story—laminated 4x5" books from ~$27.95 (6x6" $39.95) with Flickr/Picasa uploads; Pintsize Productions—design from scratch on thick paperboard with optional finger tabs; Treasured Ink—10-page 8x8 ($39.95) or 6x6 ($29.95), add pages for $3 each, professional cardstock durability.

Read post

How to Use Google Docs to Get Continuous User Feedback

July 26, 2011 4 minutes

Get feedback with Google Forms and a script. In ~5 minutes per survey you’ll get emails and a spreadsheet. Steps: create a form, allow anyone to respond, paste gist script in Script Editor, set to_email, and enable On form submit triggers with immediate notifications; email yourself the form URL.

Read post

Didn’t Get Into TechStars? Don’t Sweat It

July 22, 2011 3 minutes

If you didn’t get into TechStars, pivot: get a job at Google, work 9–5, and dedicate nights and weekends to your startup. Use day-job cash to fund contract dev/design for validation and seed money, and secure IP with a lawyer and employer blessing—don’t let rejection stop you.

Read post

Showing 1 to 10 of 44