HNHacker News
TopNewBestAskShowJobs

adamhowell

7,446 karma · joined July 6, 2007

AdamHowell.org (https://adamhowell.org)

Hard Work Montage (https://hardworkmontage.com)

submissionscomments
adamhowell··on Qwen Image 2.1
Claude and I have spent most of the summer on exactly this problem for Skechworks (skechworks.com), a free little Mac design app I made to help my own workflow that is very similar to yours. I use it for my custom coin shop The Achieve Mint (theachievemint.com).

It runs VTracer under the hood too. Most of the cleanup you're doing in Inkscape could possibly be pushed to before and after the trace?

Skechworks picks the palette before the trace and forces it again after. I quantize to 8 colors with pngquant, trace, then snap every fill back to the nearest palette color. VTracer fills each region with its own average color, otherwise you get hundreds of nearly identical grays. One design went from 279 fill colors to 3.

I upscale 2x before I quantize. The anti-aliasing is what tells the tracer where an edge really sits. Quantize at 1x and you throw that away, and small text comes out lumpy. Related gotcha: filter_speckle is an area, so don't double it when you double the image.

I also flatten transparency onto white first. VTracer counts every alpha value as a different color. I had a 5 color picture that it saw as 688 colors, and the trace took 6 GB of memory. Flattened, the same picture took 300 MB.

For the background I sample the whole edge of the picture. If 85% of it is one color, I delete every path in that color that touches the edge. White inside the drawing never touches the edge, so it stays.

For black and white I threshold with Otsu, then trace in color mode with hierarchical stacked instead of bw mode. bw mode hands you one giant black path full of holes. Stacked gives you every region as its own shape, which is much easier to edit. You have to pad the image with the background color first, or VTracer decides your subject is the canvas.

Your FLUX step is the same trick I use for photos and messy art. I have an image model redraw the picture as flat art, then trace the redraw. That came out about a quarter the file size of the best direct trace I could get. The catch is that the model moves and resizes the subject a little every run. I measure the box around the ink in both pictures and fit the trace back onto the original.

What I haven't solved is curve fitting. vectorizer.ai gives you real arcs and straight lines. VTracer gives you splines, so circles are never quite circles.

adamhowell··on LinkedIn Feed Blocker
Something I discovered recently: if you stop following everyone you’re connected to, Linkedin’s feed breaks so you get this by default. I can still interact with everyone normally, send messages, etc, but I do not see any Linkedin content, ads, etc. Do not miss it.
adamhowell··on Claude Opus 5
Opus 5 Pelican SVG: https://pelocan.ai/drawings/ese0s599
adamhowell··on Show HN: Pet Reminder – A macOS reminder app with a desktop pet
So, on the one hand, I want everyone to be able to vibe code all the software they always wish existed and be able to use it and enjoy it.

But, on the other hand, I don't ever want to use anyone else's vibe coded software. Especially if it's non-essential.

And I certainly won't ever pay for it.

adamhowell··on Show HN: I started treasure hunt in Blue Ridge. It's Day 7. Prize is up to $36k+
Gold has gone up 8% but just yesterday I conservatively updated the value by 4%
adamhowell··on Show HN: I started treasure hunt in Blue Ridge. It's Day 7. Prize is up to $36k+
He did not! It was all still there. Too slippery for his tiny hands!
adamhowell··on Show HN: I started treasure hunt in Blue Ridge. It's Day 7. Prize is up to $36k+
Stressful but yeah so far lots of fun.

Yeah it's a good question, because it's important to start with as much of a jolt as you can.

I launched the hunt the same day it got covered in a local popular Charlotte NC newsletter:

https://tinymoney.com/2025/10/09/treasure-hunt-nc-gold-coins...

So that helped kickstart it and was always part of the plan when I decided to actually do it.

adamhowell··on Ask HN: What are you working on? (October 2025)
Maybe some? But the circle today will be 160 miles wide or about the same width as Switzerland and Denmark. So I'm not sure how much shadows would help you pinpoint a specific location in an entire country worth of mountains.
adamhowell··on Ask HN: What are you working on? (October 2025)
Thanks! Yeah, I unfortunately can't shell out a straight $20k donation, but I saved the $25k over the year from my e-commerce business and justified it as a marketing expense if worse case scenario happens and it's found earlier than the math predicts. But if we get past break even then can't wait to write that check to help out the communities around here that are still recovering.
adamhowell··on Ask HN: What are you working on? (October 2025)
This one's going to be out of left field, but last Thursday I launched Countdown Treasure (https://countdowntreasure.com)

It's a real life treasure hunt in the Blue Ridge Mountains with a current total prize of $31,200+ in gold coins and a growing side pot.

I modeled it off of last year's Project Skydrop (https://projectskydrop.com) which was in the Boston area.

* Shrinking search area (today, Day 5, it will be 160 miles, on Day 21 it'll be just 1 foot wide)

* 24/7 webcam trained on the jar of gold coins sitting on the forest floor just off a public hiking trail

* Premium upgrades ($10 from each upgrade goes towards the side pot) for aerial photos above the treasure and access to a private online community (and you get your daily clues earlier)

* $2 from each upgrade goes towards the goal of raising $20k for continued Hurricane Helene relief

So far the side pot is $6k and climbing.

It's been such a fun project to work on, but also a lot of work. Tons of moving parts and checking twice and three times to make sure you've scrubbed all the EXIF data, etc.

adamhowell··on A $20k American-made electric pickup with no paint, no stereo, no screen
> Lack of a mobile app…

At the 6 mins and 40 seconds timestamp on this video (https://youtu.be/cq1qEjwSYkw?t=400) he shows the car app that will tell you current range, etc

adamhowell··on OpenAI releases image generation in the API
I think this is technically "image variations" and I think image variations are still only dall-e 3 for now (best I could tell earlier today from the API)
adamhowell··on OpenAI releases image generation in the API
So, I've long dreamed of building an AI-powered https://iconfinder.com.

I started Accomplice v1 back in 2021 with this goal in mind and raised some VC money but it was too early.

Now, with these latest imagen-3.0-generate-002 (Gemini) and gpt-image-1 (OpenAI) models – especially this API release from OpenAI – I've been able to resurrect Accomplice as a little side project.

Accomplice v2 (https://accomplice.ai) is just getting started back up again – I honestly decided to rebuild it only a couple weeks ago in preparation for today once I saw ChatGPT's new image model – but so far 1,000s of free to download PNGs (and any SVGs that have already been vectorized are free too (costs a credit to vectorize)).

I generate new icons every few minutes from a huge list of "useful icons" I've built. Will be 100% pay-as-you-go. And for a credit, paid users can vectorize any PNGs they like, tweak them using AI, upload their own images to vectorize and download, or create their own icons (with my prompt injections baked in to get you good icon results)

Do multi-modal models make something like this obsolete? I honestly am not sure. In my experience with Accomplice v1, a lot of users didn't know what to do with a blank textarea, so the thinking here is there's value in doing some of the work for them upfront with a large searchable archive. Would love to hear others' thoughts.

But I'm having fun again either way.

adamhowell··on Ask HN: What was an interesting project you started and finished over a weekend?
The other day I noticed shipitsquirrel.com was available, so I spent a couple evenings pair programming with ChatGPT to make a fun little Missile Command style game where you help Ship It Squirrel ship by blowing up distractions ;)

https://shipitsquirrel.com

adamhowell··on How Spotify's podcast bet went wrong
No. Daniel Elk was a CTO and then freelance developer and Martin Lorentzon was co-founder of a digital marketing company (and the initial money)
adamhowell··on Patreon Lays off 17% of Staff
I'm guessing this is the Twitter link you meant: https://twitter.com/TizzyEnt/status/1569439160561442817
adamhowell··on Handpicked No-Signup Tools
https://letsenhance.io/
adamhowell··on Email startup Superhuman lays off 22% of staff
Never heard of this before. Thanks for mentioning. Loving it so far.
adamhowell··on Implementation of Imagen, Google's text-to-image neural network, in PyTorch
Well, I'm focusing on business use cases – stock images and how Accomplice could be useful for marketing and content creation.

i.e. The ability to easily take your logo and stylize it: https://accomplice.ai/@adam/iterations/2bcc90ad-3237-486a-8d...

Create a photorealistic avatar whenever you need it: https://accomplice.ai/@adam/iterations/988b7d54-dc39-43b1-b5...

Easily remove the background of a photo: https://accomplice.ai/models/97746c4b-c6f0-49cb-ae1b-859716b...

Upscale a photo: https://accomplice.ai/models/bd4619ee-8202-4cf0-a04e-291820f...

Etc etc. AI can make all this stuff easier. And you have a sense of ownership over what you create. All in one place where you can collaborate on all of it with your team. I feel like that's valuable. It's certainly a tool I've always wanted.

But, also, as a bit of an aside – if the Googles and OpenAIs of the world are just going to bite every artist's style anyway with a mostly black box service and training set… it feels like the option for an artist to train/finetune their own model, promote it and possibly make money off of that is worth trying.

adamhowell··on Implementation of Imagen, Google's text-to-image neural network, in PyTorch
Update: Ah, found the "Tracking" setting in Sendgrid that I thought I had already turned off. Off for sure now. Thanks again for the heads up!

The confirmation link should only be going to accomplice.ai unless Sendgrid is doing some link tracking that I've just forgotten about. Could you forward that email to adam at accomplice dot ai if you get a chance. Thanks for letting me know!

adamhowell··on Implementation of Imagen, Google's text-to-image neural network, in PyTorch
I'm currently working fulltime on AI-powered design suite Accomplice (https://accomplice.ai) and if you ask me on a good day I would tell you I do think there's already huge commercial potential. On a bad day, though ;)

My current approach is a "model marketplace" (https://accomplice.ai/models) where the most popular open source text-to-image models (VQGAN+CLIP, Disco Diffusion, DALL-E Mega coming soon…), sit alongside the most popular open source style transfer models, and then finally I have the ability for a user to finetune their own models using a simple drag-and-drop tool (https://accomplice.ai/no-code-model-training).

Using this approach a user has enough models to try or train that they can have a higher hit rate. For example, Accomplice currently has finetuned models for photo realistic people (https://accomplice.ai/models/f58bfa91-bb18-406f-a0e1-db00fcf...), watercolor backgrounds (https://accomplice.ai/models/91b8a080-faca-4ff4-8b11-64b0789...), etc…

So theoretically if there were a searchable marketplace of 100s of different finetuned models people could choose from, they would use it much like an iStockPhoto and be able to create the kind of images they want instead of just downloading them.

But it's of course a constant work in progress. Slowly growing though and lots of promising stuff ahead!

adamhowell··on Beeple to Auction a Real-Life LED Sculpture for About $15M at Christie’s
Video of the sculpture:

https://www.youtube.com/watch?v=fIx4D3WSeHY

adamhowell··on Lofi beats with nice bass to listen while you code, study or work
Of course. I added credit and link to the playlist in the description once I finished moving all the songs over.
adamhowell··on Lofi beats with nice bass to listen while you code, study or work
Thanks for sharing!

For Apple Music users I've duplicated this playlist here:

https://music.apple.com/us/playlist/lofi-beats/pl.u-Zm4Girz7...

adamhowell··on Show HN: Create, organize, and share AI images with Accomplice
Hello HN!

I’ve dreamed for years of creating an AI tool that would 1) allow ANYONE to effortlessly create while also 2) being good enough to help augment small businesses, startups, and professional designers as well.

I’ve started and stopped on it so many times. But the technology was always just not quite there yet.

But this year, with the January release of OpenAI’s CLIP model, and the AI community’s absolutely amazing open source work on VQGAN, it all finally came together and become possible in a simple, affordable – while still limitlessly powerful – general purpose tool.

You can see what the community has already started creating here: https://accomplice.ai/community

With Accomplice, I want to help encourage and enhance the world’s creativity through AI, and I would love to hear what HN thinks.

(Note: Accomplice is powered by big beefy Nvidia GPUs so I am very aggressive with the paywall to keep the queue manageable. You'll have to pay to try it out. But as a solo business I've priced everything as reasonably as I can right now. I hope to potentially be able to lower costs though as the business grows.)

adamhowell··on Less than half of Americans know that alcohol is a carcinogen
I wasn't being facetious, I was just referencing the American Cancer Society's list:

https://www.cancer.org/cancer/cancer-causes/general-info/kno...

Arsenic is considered a carcinogen:

https://www.cancer.org/cancer/cancer-causes/arsenic.html

adamhowell··on Less than half of Americans know that alcohol is a carcinogen
I've personally found, when people ask why I'm not drinking, that "Well, did you realize Alcohol is right above Arsenic on the carcinogen list?" is by far – compared to "Oh, I just don't drink" or the other reasons I've given in the past – the fastest way to move onto other topics.
adamhowell··on Patreon Raises $90M Series E at $1.2B Valuation
They link to Jack's video in the post

https://www.youtube.com/watch?v=o4PnSJDIJMg

But since COVID he's been posting on his channel a lot more frequently and – knowing his dayjob – the production value and time he spends on these things is really impressive

https://www.youtube.com/channel/UCbd-QOxzNKQifQfSuaH5I0A

Now, he's been making videos for a long time, and obviously knows his way around producing great content, but still highly recommended.

adamhowell··on Slate, create beautiful, responsive API documentation
I just recently went with Postman's API docs for these same reasons. Having used Postman to test while building out my API, it was refreshingly easy to take the extra steps of doing everything "properly" – fleshing out the rest of the variables by pulling out any static values, creating extra descriptions in Markdown, etc – in order to publish it as living documentation.
adamhowell··on ‘Success Addicts’ Choose Being Special over Being Happy
The book "Aging Well" goes into detail about the men themselves, the study perimeters, and the interviews they conducted:

https://www.amazon.com/Aging-Well-Surprising-Guideposts-Deve...

None of these guys led perfect lives. Alcoholism, abuse, death, divorce. But as they grew older the things they most often cited in hours of interviews as objectively making them happier, were the relationships they forged and kept along the way.

Page 1 of 12Next →