Activity
Mon
Wed
Fri
Sun
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
What is this?
Less
More

Created by Brandon

Big Picture Data

Private • 1 • Free

Data is just the glyphs on the canvas of the world, it's one part of the BIG Picture. We're here to explore what it all means, building along the way.

Memberships

Organic Money

Private • 98 • Free

Q's Mastermind

Private • 3.3k • Free

Data Alchemy

Public • 14.4k • Free

LogikBot

Public • 17 • Free

Data Freelancer

Private • 52 • Paid

Skool Community

Public • 80.5k • Paid

The Skool Games

Private • 12.4k • Free

322 contributions to Data Alchemy
Can someone be my mentor and guide me?
Hi I hold an MS degree in Telecommunication Engineering and have accumulated 13 years of experience as a Computer Network Routing/Switching and Network Security Engineer in a mobile operator company. I am now keen on transitioning into the field of AI engineering or exploring how AI can enhance computer network routing, switching, and network security. Would you be willing to share your expertise or guide me if you have encountered a similar career transition? Would someone be willing to serve as my mentor and provide guidance? Thank you for your time and consideration. BR
4
2
New comment 2d ago
2 likes • 2d
I moved into this space from infrastructure, I got to flex a little BGP and OSPF configuration "back in my day", before I moved to working with cloud services, which is less intensive imo. I don't know about mentorship, but if you have questions as you start learning, the community and myself will happily try to help! Maybe you'd do well to apply it to packet captures, package vulnerabilities, or heck... Maybe you go down the path of LLM agents for OSINT recon. Regardless, it's green pastures, most cases you try you'll find there isn't a ton of others trying. The first step is just using them every chance you get! 😁
How to build reliable systems with LLMs
Are you using the OpenAI API in your projects? If so, then I'm going to tell you right now that there is probably a better way to do that. In this video, I share everything that you need to know about getting structured output from OpenAI in order to build more reliable systems with LLMs. We compare prompting techniques, JSON mode, function calling, and the Instructor library to find the best way to integrate OpenAI models into applications. The video is linked below. I hope you find it helpful. If you do, consider subscribing :)
31
25
New comment 17h ago
4 likes • 2d
Loved how you applied it to a real world use case. Thanks for the insight here!
Free Data Sets
here's some free datasets from the Google Analytics course: 1. U.S. government data site: Data.gov is one of the most comprehensive data sources in the US. This resource gives users the data and tools that they need to do research, and even helps them develop web and mobile applications and design data visualizations.  2. U.S. Census Bureau: This open data source offers demographic information from federal, state, and local governments, and commercial entities in the U.S. too.  3. Open Data Network: This data source has a really powerful search engine and advanced filters. Here, you can find data on topics like finance, public safety, infrastructure, and housing and development. 4. Google Cloud Public Datasets: There are a selection of public datasets available through the Google Cloud Public Dataset Program that you can find already loaded into BigQuery.   5. Dataset Search: The Dataset Search is a search engine designed specifically for data sets; you can use this to search for specific data sets.
8
7
New comment 1d ago
3 likes • 2d
Here's another resource for public data sets as well. I'm going to do a data project on the Harvard Economic data soon! https://github.com/awesomedata/awesome-public-datasets
👋🏻 Welcome to Data Alchemy — Start Here
The goal of this group is to help you navigate the complex and rapidly evolving world of data science and artificial intelligence. This is your hub to stay up-to-date on the latest trends, learn specialized skills to turn raw data into valuable insights, connect with a community of like-minded individuals, and ultimately, become a Data Alchemist. Together, let's decode the language of data and shape a future where knowledge and community illuminate our way. Rules - Don't sell anything here or use Data Alchemy as any kind of funnel - We delete low effort community posts, and posts with poor English. Proofread your post first. - Help us make the posts high quality. If you see a low quality post, then click on the 3 dots on the post and "Report To Admins". Start by checking out these links - Classroom - Introduction - Roadmap - Contribution Be Aware of Scammers - Please be aware that this is a public group. Unfortunately, some people abuse the Skool platform to send DMs or post comments to trick people. This is the internet, so always do your own due diligence. Never automatically trust someone here on the Skool platform other than @Dave Ebbelaar's official account. To kick things off, please comment below, introducing yourself. Let us know: 1. Your name and where you're from 2. What project(s) you're currently focused on See you in the comments!
Complete action
436
5.3k
New comment 5h ago
3 likes • 4d
@Wilson So Nice! You already have the Ops super power. You'll be a beast when you get these data ai skills. :D
5 likes • 4d
@Royous Zacharias I still haven't learned how to effectively test lol. Love the diversity here though. Welcome to the group!
DSPy 🤯
Wow! I haven't fully wrapped my head around this , but I had to share. > Understanding DSPy > Imagine a toolkit so powerful yet intuitive that it empowers even those with a basic grasp of programming to craft their own AI companions. From: https://www.graybook.ai/blog/building-an-ai-assistant-with-dspy
4
7
New comment 5d ago
2 likes • 5d
This is a very interesting framework. I started getting back up to speed with it this weekend. One of my goals is to use it to optimize a prompt that Phi-3 will be able to use to complete a common tasks I test on.
2 likes • 5d
@Anaxareian Aia I like to have a general sense of the remote job market, so I have a dashboard that displays output from what I can a "Business Value" task. Here's the site that makes it easier to read, that I made using Claude 3: https://display.datastrain.io/ Here's the raw logs so you get an idea of the prompt and raw output: https://langfuse.datastrain.io/project/cluve1io10001y0rnqesj5bz4/traces/c3c7a85d-e6a9-4e85-b650-6e08c7c51191?observation=time-18-21-13-399425_2d42bb36-f139-4e19-a7dd-c3dbc101ec8d Claude 3 Haiku is very good at giving JSON output, although llama3-70b, with comparable speed, is good to... The quality seems worse than Haiku though. about 0.52-60 cents for almost 1 million tokens: https://langfuse.datastrain.io/project/cluve1io10001y0rnqesj5bz4/traces/3ac832ba-bd50-4e8e-9e9f-6233947df330 Finally, Phi 3 still does pretty good at JSON output, but on "simpler" task: https://langfuse.datastrain.io/project/cluve1io10001y0rnqesj5bz4/traces/2c214c49-d09b-47de-bf45-aa9f9e8289fc?observation=time-14-23-24-362485_chatcmpl-ab525398-3e8c-4e0c-9950-9ae4c1379256 What's your MVP?
1-10 of 322
Brandon Phillips
6
156points to level up
@brandon-phillips-8784
Solutions Architect turned Data Synthesizer, interested in how we turn this stuff into useful things to people.

Active 3h ago
Joined Sep 22, 2023
INFP
Utah, United States
powered by