Thanks! We started as a 501(c)(3) nonprofit focused on after-school programming clubs and high school hackathons. We were working with high schoolers across the country and noticed that teenagers lacked the necessary financial infrastructure to run in-person events. For example, receiving money from a sponsor to buy pizza. We built HCB to give them essential tools like a donation page, invoicing system, and debit cards.
Since then, it's grown to a platform that supports not only high school hackathons, but nearly any nonprofit-related mission, including robotic teams and local food banks. We're still an educational nonprofit centered around high school coding clubs, but HCB is a tool we maintain to better empower these high schoolers.
Honestly though... let's take Copilot as an example. if they're good with Copilot, why wouldn't you just hire them and let them be good with copilot? We all just need to accept that the value of memorizing syntax will trend to zero.
LlamaIndex docs, LangChain docs, Youtube vids on intro to neural networks, tutorials on RAG, cross encoders, etc. should keep you busy for 20-40 hours at least
I am a seasoned engineer with deep experience building full stack AI applications. Whether you're building a tool for search, travel, exploring vector databases or RAG - I can architect the first version and get it to market for you.
I can also program smart contracts, write React Native apps, or work on backend and frontend projects. I've had one exit as an early fintech employee, so I have the experience/know how to iterate and launch quickly.
Feel free to shoot me a message at david @ callstop <dot> com and we can talk about your specific project and how I'd build it.
SEEKING WORK - Location: PST - Remote Consulting: Yes
I have a deep understanding of AI infra/architecture patterns if that is needed. I'm a seasoned senior engineer and have helped 3 YC companies launch & have worked on and at multiple startups, as well as big tech. I work for and consult for startups launching MVPs and new services, particularly with LLMs, React/RN and solidity. 6.5+ years of professional experience, especially in fintech + AI. Check out my submission history for just a few examples of products I've built.
Willing to relocate: No
Technologies: 6.5+ yrs professional experience; JS, React, React Native, Python, Node, AWS, Java, Heroku, Dynamo, Mongo, MySQL, Ethereum (Solidity), REST, Docker
Résumé/CV: https://www.linkedin.com/in/deejax/
Email: david <@> callstop <d 0 t > com
You're probably better off analyzing how different models work with different RAG subjects/content.
It will proxy the work you're trying to do of analyzing models trained on different datasets. Find an HF model trained on natural lang/web, one on code etc.
- I predict that we will see the tangible effects of AI eating into non-technical areas (insurance, content creation, chatbots via RAG + agents) more and more.
- We will continue to see price gouging in utilities and rent, driven by corporate greed.
- Tesla will continue to dominate the electric car market, and Rivian will also make it.
Chunking is one of those things that needs to be custom to the document being processed.
As a general rule, try recursive chunking for most questions. Consider using multiple strategies in tandem. It has the nice advantage of incorporating both broad and specific context.
However, even the document itself is not enough to design a chunking strategy. Consider an HTML document and the questions:
1. How does that webpage code work?
2. Summarize this website.
As you can see, you might benefit from pre-processing info different based on the intended result. One cares strongly about the tags, styling etc. while one only cares about the text and you could maybe just scrub the tags.
Also, consider chunks overlap and max chunk size and tune them based on different trials.
Check your chunk scores (cos similarity) against sample queries and make sure chunks texts are meaningful. "Is this how I would store info in my head?" might be a good way to start, if your chunks are garbage you will get garbage.
Consider visualizing your chunks in clusters to validate topic relevance.
Last thing a RAG is a multi-step arch., only one step being bad will turn the whole thing to garbage, put lots of debugging, eval steps in yours. Make sure its not the prompt step thats ruining it. Identify the weak points and triage accordingly.
SEEKING WORK - Location: PST - Remote Consulting: Yes
I'm a seasoned senior engineer and have helped 3 YC companies launch & have worked on and at multiple startups, as well as big tech. I work for and consult for startups launching MVPs and new services, particularly with LLMs, React/RN and solidity. 6.5+ years of professional experience, especially in fintech + AI. Check out my submission history for just a few examples of products I've built.
Willing to relocate: No
Technologies: 6.5+ yrs professional experience; JS, React, React Native, Python, Node, AWS, Java, Heroku, Dynamo, Mongo, MySQL, Ethereum (Solidity), REST, Docker
Résumé/CV: https://www.linkedin.com/in/deejax/
Email: david <@> callstop <d 0 t > com
