Jesus Romero

🚀 Agile Techie PM | Bridging Tech-Business Gaps 💼 | Project Manager & Tech Enthusiast | Exploring the Intersection of Tech and Business 💡 | Speaker & Content

[Agile Scrum Guide @AgileScrumGuide]

Leverage the 5 Phases of Team Development — #Forming, #Storming, #Norming, #Performing, and #Adjourning — to help your teams (Agile/Scrum or otherwise) be more successful. For details including permission request info., high-res files, and more, visit: https://t.co/3xHGytC2QT.

[Google Cloud @googlecloud]

Next from #GoogleCloudNext:

Introducing our upcoming #generativeAI search packaged solution powered by Gemma—our state-of-the-art open models—to help retrieve & analyze data at the edge or on-premises with GDC. Learn how we're empowering AI everywhere ↓
https://t.co/JkUoSMG8Rc

[Jesus Romero @AgileTechiePM]

I am a Google Cloud Innovator! Learn more about how you can join our developer community too. #GoogleCloudInnovators https://t.co/cV918UTMNg

[Google Cloud Tech @GoogleCloudTech]

It's time for the #GoogleCloudNext Opening Keynote. Tune in now↓

https://t.co/OARNoUmUkM

[Jesus Romero @AgileTechiePM]

#RAG

[LangChain @LangChain]

RAG From Scratch: Query Structuring

Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code.

This is the 11th video in our series and focuses on query structuring.

🔧 Problem: We interact w/ databases using domain-specific languages (e.g., SQL, Cypher for Relational and Graph DBs). And, many vectorstores have metadata that can allow for structured queries to filter chunks. But RAG systems ingest questions in natural language.

💡 Idea: A great deal of work has focused on query structuring, the process of text-to-<DSL> where DSL is a domain specific language required to interact with a given database. This converts user questions into structured queries. Below are links that dive into text-to-SQL/Cypher, and the below video overviews query structuring for vectorstores using function calling.

📽️ Video:
https://t.co/QcreSMm60W

💻 Code:
https://t.co/sglvEoOjx9

🧠 References:
1/ Blog with links to various tutorials and templates:
https://t.co/Vw5Zb4HDFu
2/ Deep dive on graphDBs (c/o @neo4j):
https://t.co/0e4NYimlOd
3/ Query structuring docs:
https://t.co/vBHVd1QDi5
4/ Self-query retriever docs:
https://t.co/1SjgOHAFM3

[Jesus Romero @AgileTechiePM]

@GeostatsGuy Excellent, thanks for sharing!

[Jesus Romero @AgileTechiePM]

Some underlying non-ROl metrics support the entire project and products, like columns in a structure. As PMs, we must care for them throughout the project/ product lifecycle.

What's ONE non-ROI metric that's made a surprising difference in your projects?

#ProjectManagement

[Jesus Romero @AgileTechiePM]

It is better to have a great business model behind a mediocre technology than the best technology behind a mediocre business model.
#projectmanagement #technology #AI #ML

[Jesus Romero @AgileTechiePM]

A simple answer to ‘WHAT FOR’ can solve even the most complex data problems in projects.
#DataScience #ProjectManagement #Agile

[Jesus Romero @AgileTechiePM]

🤔 Ever been in my spot? That dread you caused the problem by trying to be super responsive? Share how you navigated it 👇...let's normalize talking about these PM near-misses.
#projectmanagement #stakeholdermanagement

[Jesus Romero @AgileTechiePM]

Projects blowing up from focusing ONLY on pleasing the client? This nearly wrecked ours 😅 ...a thread on the hidden stakeholder mistake too common for PMs 🧵

[Jesus Romero @AgileTechiePM]

Communication saves the day (again!) 💪 Once everyone saw the impact chain of one 'small' client request, priorities got reset. This is Project Management - it's never static plans! 📈

[Quincy Larson @ossia]

freeCodeCamp YouTube channel update: we just hit 9 million subscribers. 🚀

We've now published more than 1,000 FREE full-length courses on math, programming, and computer science. 🏕️

[Jeff Dean @JeffDean]

I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks, including 10 of 12 popular text and reasoning benchmarks, 9 of 9 image understanding benchmarks, 6 of 6 video understanding benchmarks, and 5 of 5 speech recognition and speech translation benchmarks. Gemini Ultra is the first model to achieve human-expert performance on MMLU across 57 subjects with a score above 90%. It also achieves a new state-of-the-art score of 62.4% on the new MMMU multimodal reasoning benchmark, outperforming the previous best model by more than 5 percentage points.

Gemini was built by an awesome team of people from @GoogleDeepMind, @GoogleResearch, and elsewhere at @Google, and is one of the largest science and engineering efforts we’ve ever undertaken. As one of the two overall technical leads of the Gemini effort, along with my colleague @OriolVinyalsML, I am incredibly proud of the whole team, and we’re so excited to be sharing our work with you today!

There’s quite a lot of different material about Gemini available, starting with:

Main blog post: https://t.co/NzSycJl7aE

60-page technical report authored by th Gemini Team: https://t.co/CEdMRyYSLo

In this thread, I’ll walk you through some of the highlights.

[Jesus Romero @AgileTechiePM]

✌️🤖

[OpenAI @OpenAI]

We have reached an agreement in principle for Sam Altman to return to OpenAI as CEO with a new initial board of Bret Taylor (Chair), Larry Summers, and Adam D'Angelo.

We are collaborating to figure out the details. Thank you so much for your patience through this.

[Jesus Romero @AgileTechiePM]

❤️

[Sam Altman @sama]

i love the openai team so much

[365 Data Science @365datascience]

Join us at 365 Data Science as we open the doors to our platform from Nov. 6 to Nov. 20. Learn new data and AI skills to stay current in a dynamic job market for FREE. Sign up today—no credit card or payment required. ➡️
https://t.co/CE1aDBStfI

[OpenAI @OpenAI]

GPTs are a new way for anyone to create a tailored version of ChatGPT to be more helpful in their daily life, at specific tasks, at work, or at home — and then share that creation with others. No code required. https://t.co/SPV4TcMiQw