HackerTrans
TopNewTrendsCommentsPastAskShowJobs

jarulraj

no profile record

Submissions

Ask HN: Has the CS curriculum been dumbed down over the past decade?

1 points·by jarulraj·3년 전·3 comments

Ask HN: How is the community using LLMs for data cleaning/enriching/structuring?

7 points·by jarulraj·3년 전·10 comments

Show HN: Stargazers Reloaded – LLM-Powered Analyses of Your GitHub Community

20 points·by jarulraj·3년 전·5 comments

[untitled]

1 points·by jarulraj·3년 전·0 comments

MindsDB vs. EvaDB: Connecting AI Models to Database Systems

medium.com
12 points·by jarulraj·3년 전·0 comments

Ask HN: How has your experience been with using AI Agents?

5 points·by jarulraj·3년 전·5 comments

PrivateGPT in SQL

github.com
7 points·by jarulraj·3년 전·0 comments

Show HN: EVA – AI-Relational Database System

github.com
237 points·by jarulraj·3년 전·36 comments

comments

jarulraj
·12개월 전·discuss
:)
jarulraj
·12개월 전·discuss
Agreed, I just updated it to "Elements of System Design".
jarulraj
·12개월 전·discuss
I added it now :)
jarulraj
·12개월 전·discuss
Yes :)
jarulraj
·12개월 전·discuss
Exactly. It is intentionally open-ended: new "principles" can emerge, split, or retire as the taxonomy evolves. This is just version 1. The grid is a visual index and the fun part is mappin systems to "molecules" in different domains like OS, databases, computer architecture, distributed systems, programming languages, networking, and more..
jarulraj
·12개월 전·discuss
Yes, I just borrowed the periodic table metaphor. "Elements of System Design" is a better name.
jarulraj
·12개월 전·discuss
Author here, great question :) If principles are the elements, we can think of each system as a "molecule" with some imagination. For example, an SQL database system has many principles:

1. Abstraction Lifting (Al) + Policy/Mechanism Separation (Pm): SQL states high-level intent with precise semantics, and logical operators are decoupled from physical operators.

2. Equivalence-based Planning (Ep) + Invariant-Guided Transformation (Ig): We apply algebraic rewrites that preserve semantics (e.g., join reordering, predicate pushdown) under stated invariants.

3. Cost-based Planning (Cm): We choose concrete physical operators and join orders using a cost model and so on..
jarulraj
·12개월 전·discuss
Totally fair.. I am not claiming periodicity here :) I just wanted to use the "periodic table" as a visual metaphor. The goal is to outline a mostly orthogonal set of system design principles and illustrate cross-domain connections to students so that it is easier to compare trade-offs and discuss designs more precisely.
jarulraj
·12개월 전·discuss
Author here, appreciate the share :) I was not expecting this to get so much attention.

To clarify: this is indeed just a taxonomy of classic system-design principles. The periodic-table styling is a familiar metaphor; there is no claim that principles repeat periodically. The goal was to outline a mostly orthogonal set of design principles and highlight cross-domain connections across computer systems so it is easier to discuss designs precisely. Thanks for all the thoughtful feedback!
jarulraj
·3년 전·discuss
It is based on the feedback shared by an undergraduate student -- pretty subjective. For instance, it is possible to graduate with a CS degree without even taking an introductory course on systems.
jarulraj
·3년 전·discuss
It is currently not possible to get rigorous summaries of paper chunks using GPT-4.
jarulraj
·3년 전·discuss
Wouldn't more semantically related neighbors be retrieved by just increasing K?
jarulraj
·3년 전·discuss
Cool project! Can you elaborate on "scalable" AI deployment? We are exploring the data + AI space in EvaDB and would love to exchange notes [1].

[1] https://github.com/georgia-tech-db/evadb
jarulraj
·3년 전·discuss
Very cool project, @MatthausK!

What are your thoughts on reducing LLM cost?

We are also exploring LLM-based data wrangling using EvaDB and cost is an important concern [1, 2, 3].

[1] https://github.com/georgia-tech-db/evadb

[2] https://medium.com/evadb-blog/stargazers-reloaded-llm-powere...

[3] https://github.com/pchunduri6/stargazers-reloaded
jarulraj
·3년 전·discuss
Nice :)

What were the interesting problems you faced in processing the survey data?

If possible, can you share the prompt?
jarulraj
·3년 전·discuss
As we do not have ground truth, we only qualitatively checked for accuracy -- no quantitative metrics. We did find a significant drop in accuracy with GPT 3.5 as opposed to GPT 4.

Are you measuring accuracy with data wrangling prompts? Would love to learn more about that.
jarulraj
·3년 전·discuss
Yes, there is definitely a human-in-the-loop element here.

It would be great if you could share an example of the inconsistent output problem -- we also faced it. GPT-4 was much better than GPT-3.5 in output quality.
jarulraj
·3년 전·discuss
Great question! We iterated on the prompt for several days and manually verified the results for ~100 users.

The results were pretty good: https://gist.github.com/gaurav274/506337fa51f4df192de78d1280...

Another interesting aspect was the money spent on LLMs. We could have directly used GPT-4 to generate the "golden" table; however, it's a bit expensive — costing $60 to process the information of 1000 users. To maintain accuracy while reducing costs significantly, we set up an LLM model cascade in the EvaDB query, running GPT-3.5 before GPT-4, leading to a 11x cost reduction ($5.5).

Query 1: https://github.com/pchunduri6/stargazers-reloaded/blob/228e8...

Query 2: https://github.com/pchunduri6/stargazers-reloaded/blob/228e8...
jarulraj
·3년 전·discuss
Thanks for your kind words, @skeptrune! It was certainly a fun project.

We found some interesting insights. In the Langchain community, ~40% of the stargazers are from India. In the GPT4All community, we found that web developers love open-source LLMs -- more so that machine learning folks :)

Curious if there is any reason why you would not use it?
jarulraj
·3년 전·discuss
Thanks for your kind words, @treebeard5440! :)