thecolorblue

As much as rich people can do whatever they want if they hand over enough money, it seems like these people will not be rich for long if they fork over this much money for a single day experience.

Location: Cleveland, Ohio

Remote: yes

Willing to relocate: no

Technologies: MCP servers, agents, agent harnesses, LLM evals, javascript, typescript, python, SQL, Docker, AWS, GCP

Résumé/CV: https://docs.google.com/document/d/1pGfDBQkmiCBsoDr0_nInqw6S...

Email: brad.bdavis1@gmail.com

I am a senior software engineer with 13 years of experience with javascript, 6 with typescript, and 5 with python and full stack development. I have worked in Biotech, life sciences, e-commerce, and SaaS. Most recently I have been evaluating LLM output at Micro 1.

I have been working on an AI harness for building desktop applications from SPEC.md files, along with some examples SPEC.md files I have tested, at https://specliotheque.com. The agent harness is available here: https://github.com/thecolorblue/bspec

I always come back to this quote:

“Once men turned their thinking over to machines in the hope that this would set them free. But that only permitted other men with machines to enslave them.” ― Frank Herbert, Dune

I have gotten into spec driven development. Plan everything ahead of time. Sometimes I have the LLM help out, sometimes I do it all myself. It can include data models, business logic, or UI design. Sometimes I draw on a whiteboard, or in a notebook, and ask the LLM to convert the drawing into text I can put into a SPEC.md file. The more time I spend planning, the longer the LLM can work autonomously, and the less time I spend debugging issues or asking it to fix things that I didn't ask for.

Some people put significant time into their blogs. It is not cheap to add value through writing.

You could either go down the 2d isometric map route (something like animal crossing) or something closer to google maps (maybe with mapbox studio?).

The current map feels more like a menu to me.

I love it! I signed up to be the groundskeeper.

I really want a 2d world so I can see everything going on in the game. Even a static map would help visualize what the game is about.

I honestly don't understand this statement. What else besides healthcare could fix that? Are you arguing that Mississippi obesity is due to genetics and cannot be changed?

The only other thing I can think of that would affect state wide obesity is food security and quality. Proper healthcare would be my first pick for fixing obesity.

Location: Cleveland, Ohio

Remote: yes

Willing to relocate: no

Technologies: MCP servers, agents, AI harnesses, javascript, typescript, python, SQL, Docker, AWS, GCP

Résumé/CV: https://docs.google.com/document/d/1pGfDBQkmiCBsoDr0_nInqw6S...

Email: brad.bdavis1@gmail.com

I am a senior software engineer with 13 years of experience with javascript, 6 with typescript, and 5 with python and full stack development. I have worked in Biotech, life sciences, e-commerce, and SaaS. Most recently I have been building AI agents for evaluating LLM output at Micro 1.

I have been working on a AI harness for building desktop applications from SPEC.md files, along with some examples SPEC.md files I have tested, at https://specliotheque.com .

PE profits sound like other companies opportunities. Unless there are barriers to entry not covered in this article, I would think other companies could move in, deliver a fire truck faster and at a lower cost, and at least take a portion of the market that is able to switch.

I am a software engineer with 13 years of experience with javascript, and 3 years at a full stack developer with python. I have experience with SaaS, deploying and maintaining ML models in production, Biotech R&D, and LLM workflows. My latest project is a LLM career coach that guides you through achieving your goals and keeps you focused, based on enneagram and emotional intelligence scores.

https://github.com/thecolorblue/coach-loop

Location: Cleveland, Ohio

Remote: yes

Willing to relocate: no

Technologies: react, typescript, python, postgresql, AWS, GCP, LLM agents

Résumé/CV: https://docs.google.com/document/d/1pGfDBQkmiCBsoDr0_nInqw6S...

Email: brad.bdavis1@gmail.com

I am a software engineer with 13 years of experience with javascript, and 3 years at a full stack developer with python. I have experience with e-commerce, SaaS, deploying and maintaining ML models in production, and Biotech R&D. My latest project was a LLM powered chrome extension that used webMCP and experimental chrome APIs to search amazon for products. https://github.com/thecolorblue/amazon_webmcp_demo

Location: Cleveland, Ohio

Remote: yes

Willing to relocate: no

Technologies: react, typescript, python, postgresql, AWS, GCP, LLM agents

Résumé/CV: https://docs.google.com/document/d/1pGfDBQkmiCBsoDr0_nInqw6S...

Email: brad.bdavis1@gmail.com

I have been working on my own language arts app for k-12 (https://snowdayacademy.com). In my experience, if it's not fun or rewarding, nobody is going to use it. Most of my users are parents that want their kid to get better grades, or the students want a better studying experience. So, for me its a combination of interesting content, UX, and better feedback than doing a worksheet.

I have been testing it with my two daughters and they make it very clear when its to painful to be useful.

The other thing that worked for me was talking to experts, in my case reading specialists.

https://snowdayacademy.com

Reading practice and assessments for k-12 students, with reporting and tracking for parents, tutors, and teachers. It uses speech to text and quizzes to assess the students reading ability. It picks up skipped words, substituted words, along with metrics on speed and pauses.

I have been testing it with my 2 daughters and its finally at a spot where I don't have to drag them to test it against their will and they are showing improvement. I am working on the marketing now. I have gotten some interest from private tutors but I have a feeling it will be great for the homeschooling community.

Thanks for any feedback! Please leave first reactions as the marketing page is what I am iterating on right now. Don't hold back!

Location: Cleveland, Ohio

Remote: Yes

Willing to relocate: No

Technologies: JS, typescript, next.js, react.js, python, pandas, SQLAlchemy, Fast API, SQL, AWS, GCP

Résumé/CV: https://docs.google.com/document/d/1uuq8KB2uVcMB0l5zJR-8Nruc...

Email: brad.bdavis1@gmail.com

13 years of experience with javascript, 6 with typescript and python. I'm currently working on launching a react native app. I have experience in e-commerce, SaaS, and biotech.

Hi, I'm Brad, software engineer, long time HN lurker. I have been working on this project for a while and I think it is ready for more feedback. I have been calling it Snow Day Adventures, an app for k-12 students home from a school snow day that beats watching YouTube or Instagram.

One of the things I consistently used chatGPT for is creating bedtime stories for my two daughters. They were never very long, but we could customize them and ask for edits. It was a fun activity we could do laying down before bed.

Fast forward to just about a year ago when an administrator at my daughter's school reached out about AI. We had a meeting where we talked about the basics but I really had no idea how AI would work in K-12 education. There were a couple apps that they use, which were fine, but I felt like they did not take advantage of the technology. At the same time, I was not qualified to give them advice.

So I started building little apps here and there. I would test them with my daughters. Usually they would get bored or it would feel to much like homework. Sometime this summer I focused on generating engaging stories and came up with a workflow for generating choose your own adventure stories. After a couple iterations, I got to where the app is now: turn any story into a choose your own adventure.

I have loaded a couple public domain stories to start with. The idea is pretty simple: pick a story, you will see the first page and at the bottom you will see a link to the original story the author wrote and three generated pages. Once you pick a generated page, you will only see generated options (and you will probably see the options take ~10 seconds to load). You can also click the refresh button which will replace that page with a new generated one.

The generated pages are never as good as the originals, but it does make it more fun. Going back and trying different paths creates endless amounts of content. I think the bigger opportunity is to customize the stories to the students reading level and language abilities. I did a couple tests with bi-lingual story generation, and generating from a strict lexile reading level; both showed some promise.

I know it does not technically need a user to log in, but I am a little worried about story generation getting out of hand from bots. If anyone has any ideas for preventing a search engine bot from clicking every link on a page that generates new content, I would be happy to find an alternative. Maybe you have to log in to generate new content but the already generated content is public? Let me know what you think.

Thanks for taking a look.

Location: Cleveland, OH, United States

Remote: Open to remote, hybrid, and in-person

Willing to relocate: No

Technologies: JavaScript (13 yrs), TypeScript (6 yrs), Python (6 yrs), React.js, Redux.js, Saga.js, Babylon.js, Webpack, SCSS, AWS (S3, ALB, EC2, Batch, Lambda, RDS), Snowflake, SQL, REST APIs, SVG.js, Git

Résumé/CV: [Resume](https://docs.google.com/document/d/1uuq8KB2uVcMB0l5zJR-8Nruc...)

Email: brad.bdavis1@gmail.com

I’m Brad Davis, a senior software engineer and product-focused developer with over a decade of experience building scalable applications, data pipelines, and AI-driven tools. At Ginkgo Bioworks, I led the development of a 5.6 TB genomic and metadata data lake supporting 120+ researchers, integrating AWS and Snowflake to streamline scientific workflows. My work has spanned creating React.js applications for lab teams, implementing machine learning pipelines, and optimizing developer workflows with AI-assisted code generation.

I’ve contributed to open-source AI projects such as RooCode and built my own educational platform, [Snow Day](https://github.com/thecolorblue/snow_day), which generates vocabulary quizzes using LLMs. My career has included both engineering and product management roles, giving me a unique ability to bridge technical and business requirements. I enjoy designing systems that make data more accessible, applications more intuitive, and teams more effective.

He would cherry pick from a random branch that was never merged back in, add two commits of style changes inconsistent with the rest of the repo, then force push.

  Location: Cleveland, Ohio, US
  Remote: Yes
  Willing to relocate: No
  Technologies: Typescript, Python, Postgres, LLMs, computer vision, bioinformatics, ecommerce, SaaS
  Résumé/CV: https://docs.google.com/document/d/1uuq8KB2uVcMB0l5zJR-8Nruca_OgRQpIkVX1Dv-p9s4/edit?usp=sharing
  Email: brad.bdavis1@gmail.com

I have loved the integration of AI feedback in github PRs. Would I be able to test out Datafruit github integration on an open source project?

I just ran a test giving the same prompt to claude, gemini, grok and qwen3 coder running locally. Qwen did great by last years standards, and was very useful in building out boilerplate code. That being said, if you looked at the code side by side with cloud hosted models, I don't think anyone would pick Qwen.

If you have 32gb of memory you are not using, it is worth running for small tasks. Otherwise, I would stick with a cloud hosted model.

I am running it on an M1 Max.

There are multiple companies that went public in that 2019 - 2021 time frame that have negative EBITDA and are hard to price because of it.

Ginkgo Bioworks, IPO Date: Sept. 2021, EBITDA: -$325m Rivian, IPO Date: Nov. 2021, EBITDA: -$455m

Beyond Meat has seen less growth than their some of these examples, but my conclusion is still the same: it would have been better for them to find their footing as a private company, then use the IPO money to expand, rather than to pour the IPO money into R&D. Publicly trading stock causes more overhead and restricts the companies ability to pivot. Investors, founders, and employees are able to cash out before the real value has been created. The money generated does not guarantee longer term success or better long term investments as much as they thought it would.

I am still bullish on many of these companies but if I were to get in my time machine back to 2019, I would have avoided investing.

My new strategy has been wait for a large swing (when IV is high) then sell puts at ~ .1 delta. Ask me at the end of the month if it works out.

We will be doing the same thing for the 90s soon.

  Location: Cleveland, Ohio
  Remote: Yes
  Willing to relocate: Yes
  Technologies: React, Typescript, Python, AWS, Postgresql, LLM apps, image segmentation / ML, datalakes
  Résumé/CV: https://docs.google.com/document/d/1uuq8KB2uVcMB0l5zJR-8Nruca_OgRQpIkVX1Dv-p9s4/edit?usp=sharing
  Email: brad.bdavis1@gmail.com

I am interested in applying LLMs and ML to applications to improve the user experience and integrating them into the software development lifecycle. I also get obsessed with company OKRs/KPIs and metrics for tracking success.

The benefit is food security, which is not immediately apparent. When specific meats become temporarily unavailable due to a hurricane, extreme heat, or supply chain issues, the alternatives will magically taste better.

I have noticed more companies trying to schedule a whole day of interviews instead of spreading a lot of interviews out. It is only slightly better, as all of the stress and mental cost is fit into one day.

I'm not sure why this is getting downvoted. I would agree on both points, as long as the relationship stays competitive and not confrontational, both at the state to state level, and country to country. I realize that is a big "if", but as long as everyone stays cool and keeps working on their own version of utopia, it will work out.

The parasite of my parasite is my friend.