davidbarker

This is pleasant coincidence. Really like your site and it's queued to send in my newsletter in the morning! Just happened to see your comment here while I was reading. Great work.

  Location: London, UK
  Remote: Yes (remote preferred; open to one day a week in central London)
  Willing to relocate: No
  Technologies: TypeScript/React, PHP/Laravel, PostgreSQL, React Native/Expo, product design/UX, AI-assisted development
  Résumé/CV: https://dvy.io
  Email: hn@davidbarker.me
  LinkedIn: https://www.linkedin.com/in/dvyio
  Seeking: Senior Product Engineer with product design ownership (permanent preferred; open to substantial contract work)

I turn unclear product problems into useful, well-designed software. I talk to customers, turn what I learn into product and technical specs, design the workflows and interface, build the system, then help launch, market, and support it. That breadth is my strongest skill: it keeps the customer problem in view throughout.

At Flowstate, I took a workforce-planning SaaS from blank repo to paid pilot in 10 weeks as sole engineer-designer. I've since owned product design, backend, mobile apps, Stripe Connect payments, AI-assisted listing tools, and infrastructure for a US trading-card marketplace.

I use and evaluate new AI models and coding workflows to make product development faster, while preserving quality through type safety, tests, CI, review, and product judgement.

I'm looking for a team that uses AI coding tools seriously, values strong product design, and keeps product builders close to customers.

  Location: London, UK
  Remote: Yes (remote preferred; open to one day a week in central London)
  Willing to relocate: No
  Technologies: TypeScript/React, PHP/Laravel, PostgreSQL, React Native/Expo, product design/UX, AI-assisted development
  Résumé/CV: https://dvy.io
  Email: hn@davidbarker.me
  LinkedIn: https://www.linkedin.com/in/dvyio
  Seeking: Senior Product Engineer with product design ownership (permanent preferred; open to substantial contract work)

I turn unclear product problems into useful, well-designed software. I talk to customers, turn what I learn into product and technical specs, design the workflows and interface, build the system, then help launch, market, and support it. That breadth is my strongest skill: it keeps the customer problem in view throughout.

At Flowstate, I took a workforce-planning SaaS from blank repo to paid pilot in 10 weeks as sole engineer-designer. I currently own product design, backend, mobile apps, Stripe Connect payments, AI-assisted listing tools, and infrastructure for a US trading-card marketplace.

I use and evaluate new AI models and coding workflows to make product development faster, while preserving quality through type safety, tests, CI, review, and product judgement.

I'm looking for a team that uses AI coding tools seriously, values strong product design, and keeps product builders close to customers.

I have no practical use for this but I want to play with it anyway. Looks cool.

Typically one email per story.

It checks every 5 minutes, and if more than one story happens to meet the criteria during that 5 minute bucket then it'll put them into one email (so the "hiring" checks appear in one email). But in reality because it's rare that 2 stories will trend within the same 5 minute bucket it ends up being one email per story.

Currently working on HN Alerts — a simple free site I made to alert me (via email) to trending stories on Hacker News.

It sends me an email once a story hits a certain number of upvotes per minute, so it's useful for keeping track of breaking news.

It'll also soon allow you to get alerted to specific words or phrases in titles. (I have one set up so the monthly hiring threads notify me as soon as they appear.)

https://hnalerts.com

No, it's never promised unlimited — it's always had usage limits: 20× the usage of their regular Pro plan, with a limit of 50 sessions per month (a session being a 5-hour window), although I don't know if they ever enforced this.

They appear to have removed reference to this 50-session cap in their usage documents. (https://gist.github.com/eonist/5ac2fd483cf91a6e6e5ef33cfbd1e...)

So even if these mystery people Anthropic reference who did run it "in the background, 24/7", they still would've had to stay within usage limits.

  Location: London, UK
  Remote: Yes
  Willing to relocate: No
  Technologies: TypeScript, React, Next.js, PHP/Laravel, Generative AI, Photoshop/Sketch/After Effects
  Website: https://dvy.io
  LinkedIn: https://linkedin.com/in/dvyio
  Email: david@davidbarker.me

I'm a multidisciplinary designer-developer with deep curiosity and a passion for building intuitive, human-centered products, particularly those leveraging generative AI.

My professional roles have typically involved much more than just coding, spanning product design, strategy, marketing, and customer support. I thrive in small, ambitious teams where I can make a tangible impact.

Outside of work, I've built successful side projects, including:

- Balance, a free web app that anonymously helps people with acute anxiety (https://balance.dvy.io/)

- AI Autotagger, an Eagle plugin currently processing over a million images and videos per month (https://community-en.eagle.cool/plugin/4B56113D-EB3E-4020-A8...)

- HN Alerts, a free notification service that sends emails when trending Hacker News stories appear (https://hnalerts.com/)

All projects listed on my personal website: https://dvy.io

---

I’m seeking product design roles at companies building meaningful products, ideally those that integrate cutting-edge AI creatively.

Thanks. Been a happy user for a few years!

Currently working on HN Alerts — a simple free site I made to alert me (via email) to trending stories on Hacker News.

It sends me an email once a story hits a certain number of upvotes per minute, so it's useful for keeping track of breaking news.

https://hnalerts.com

That's right. I made a VS Code extension to combine all the files I have open into one long string I can copy & paste.

https://marketplace.visualstudio.com/items?itemName=DVYIO.co...

Typically something like:

  Look carefully through my codebase and identify any bugs/issues, or refactors that could improve it.

  <codebase>
  …
  </codebase>

Doesn't have to be anything overly complicated to get good results. It also does well if you give it a git diff.

Pricing: $150 / 1M input tokens, $600 / 1M output tokens. (Not a typo.)

Very expensive, but I've been using it with my ChatGPT Pro subscription and it's remarkably capable. I'll give it 100,000 token codebases and it'll find nuanced bugs I completely overlooked.

(Now I almost feel bad considering the API price vs. the price I pay for the subscription.)

In theory there shouldn't be — LLMs are pretty robust to typos and usually infer the intended meaning regardless.

  Location: London, UK
  Remote: Yes
  Willing to relocate: No
  Technologies: TypeScript, React, Next.js, PHP/Laravel, Generative AI, Photoshop/Sketch/After Effects
  Website: https://dvy.io
  LinkedIn: https://linkedin.com/in/dvyio
  Email: david@davidbarker.me

I'm a multidisciplinary designer-developer with deep curiosity and a passion for building intuitive, human-centered products, particularly those leveraging generative AI.

My professional roles have typically involved much more than just coding, spanning product design, strategy, marketing, and customer support. I thrive in small, ambitious teams where I can make a tangible impact.

Outside of work, I've built successful side projects, including:

- Balance, a free web app that anonymously helps people with acute anxiety (https://balance.dvy.io/)

- AI Autotagger, an Eagle plugin currently processing over a million images and videos per month (https://community-en.eagle.cool/plugin/4B56113D-EB3E-4020-A8...)

- HN Alerts, a free notification service to send emails when trending Hacker News stories appear (https://hnalerts.com/)

All projects listed on my personal website: https://dvy.io

I’m seeking product design roles at companies building meaningful products that integrate cutting-edge AI thoughtfully and creatively.

Claude 3.5 Sonnet is great, but on a few occasions I've gone round in circles on a bug. I gave it to o1 pro and it fixed it in one shot.

More generally, I tend to give o1 pro as much of my codebase as possible (it can take around 100k tokens) and then ask it for small chunks of work which I then pass to Sonnet inside Cursor.

Very excited to see what o3 pro can do.

If you do `/cost` it will tell you how much you've spent during that session so far.

If it's useful to anyone, I made a VS Code/Cursor extension that combines all open files into one big text document.

I use it with ChatGPT's o1 pro (which can handle around 100,000 tokens).

1. Open all of the files I think are relevant

2. Use the extension to combine them

3. Copy and paste into ChatGPT

https://marketplace.visualstudio.com/items?itemName=DVYIO.co...

It disappoints me when otherwise intelligent people take him for his word at this point. Even ignoring his descent into political madness and conspiracy, he's simply not trustworthy.

Fool me once, shame on Elon. Fool me 194 times, shame on me.

Unfortunately, not Flux. They're from Midjourney, using a few Degas as a style reference.

Whatever they're doing at Midjourney is still impressive. No training needed and a better result.

It's funny you should ask. I recently released a plugin (https://community-en.eagle.cool/plugin/4B56113D-EB3E-4020-A8...) for Eagle (an asset library management app) that allows you to write rules to caption/tag images and videos using various AI models.

I have a preset in there that I sometimes use to generate captions using GPT-4o.

If you use Replicate, they'll also generate captions for you automatically if you wish. (I think they use LLaVA behind the scenes.) I typically use this just because it's easier, and seems to work well enough.

Out of curiosity, what do you think of these? https://imgur.com/a/8p7RlMe

I suspect it really needs more training examples. The problem I found when I looked for images to use was that 60% were of dancers, and from past experience, it will end up trying to fit a dancer into every image you create. But of course, there are only a (small) finite number of Degas images that you can train with.

A possible solution may be to incorporate artificial images in the training data. So, create an initial LoRA with the original Degas images and generate 500 images. From those generated images, pick the ones that most resemble Degas. Add those to the training set and train again. Repeat until (hopefully) it learns the correct style.

Awesome! :)

Happy to help! It's a lot of fun. And it becomes even more fun when you combine LoRAs. So you could train one on your face, and then use that with a style LoRA, giving you a stylised version of your face.

If you do end up training one on yourself with fal, it should ultimately take you here (https://fal.ai/models/fal-ai/flux-lora) with your new LoRA pre-filled.

Then:

1. Click 'Add item' to add another LoRA and enter the URL of a style LoRA's SafeTensor file (with Civitai, go to any style you like and copy the URL from the download button) (you can also find LoRAs on Hugging Face)

2. Paste that SafeTensor URL as the second LoRA, remembering to include the trigger word for yourself (you set this when you start the training) and the trigger word for the style (it tells you on the Civitai page)

3. Play with the strength for the LoRAs if you want it to look more like you or more like the style, etc.

-----

If you want a style LoRA to try, this one of SNL title cards I trained actually makes some great photographic images. https://civitai.com/models/773477/flux-lora-snl-portrait (the download link would be https://civitai.com/api/download/models/865105?type=Model&fo...)

-----

There's a lot of trial and error to get the best combinations. Have fun!

It's very impressive. I aim for around 50 images if I'm training a style, but only 10 to 20 if training a concept (like an object or a face).

I have a MacBook Air so I train using the various API providers.

For training a style, I use Replicate: https://replicate.com/ostris/flux-dev-lora-trainer/train

For training a concept/person, I use fal: https://fal.ai/models/fal-ai/flux-lora-fast-training

With fal, you can train a concept in around 2 minutes and only pay $2. Incredibly cheap. (You could also use it for training a style if you wanted to. I just found I seem to get slightly better results using Replicate's trainer for a style.)

Thank you!

A reasonable amount of training images (50 or so), and then I train for 2,000-ish steps for a new style.

Many of them work well with Flux, particularly if they're illustration-based. Some don't seem to work at all, so I didn't upload those!

It's trickier than I thought it would be.

Here are a few in Degar style I made after training for 2,500 steps. I'd love to hear what you think of them. To my (untrained) eye, they seem a little too defined, perhaps?

https://imgur.com/a/sqsQLPg

I'm curious to give this a go. I've been training a lot of LoRAs for FLUX dev recently (purely for fun). I'm sure there must be a way to get this working.

Here are a few I've recently trained: https://civitai.com/user/dvyio

I was impressed by Upstash's approach to something similar with their "Semantic Cache".

https://github.com/upstash/semantic-cache

  "Semantic Cache is a tool for caching natural text based on semantic similarity. It's ideal for any task that involves querying or retrieving information based on meaning, such as natural language classification or caching AI responses. Two pieces of text can be similar but not identical (e.g., "great places to check out in Spain" vs. "best places to visit in Spain"). Traditional caching doesn't recognize this semantic similarity and misses opportunities for reuse."