Yes. Memorizing syntax is now obsolete. Frameworks are generally somewhat constrained, now they can be auto-generated to be exactly the UI you want. Only caveat would be saving tokens but tokens are cheap. RIP
That's a people problem, not an AI problem. People spend so much time debating overcomplicating early system design (API v.s. event driven, etc.). AI is pretty good at generating what you want if you tell it your LOE and resources.
No doubt about the zero sum game in terms of a possible path in terms of wealth distribution. My question is what will be the function of the "sum part" as a society builds all technologies to 'completion' which is defined as when the utility of any new technology approaches zero because there is nothing 'valuable' or 'new to invent'.
A different argument is that as technology improves to infinity, wealth also becomes ubiquitous and potentially infinite. So even though no new technology is invented that is valuable, there is infinite wealth through abundance.
It seems to me that the primary driver of which world we end up in is whether humanity is able to become multi-planetary. Otherwise, resources become a constraint and instead of discovering new existing resources, humanity can only create value by inventing new technology.
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
Flexible Finance | REMOTE (US) | Fast growing fintech
Flex (https://getflex.com/) is an early-stage, remote-first FinTech startup that is bringing flexible payments to recurring bills. Flex currently offers flexible payments on rent for certain tenants in the U.S. The company is scaling quickly, and there are engineering and product positions open currently. If you want to be part of a company growing rapidly with high potential upside (#65 on the App Store in Finance as of this moment), consider joining Flex. You can apply here through my engineering referral link: https://grnh.se/474304b85us
Contact for consulting/hiring:
https://www.linkedin.com/in/deejax
david <at> callstop · com