Prashant retweeted
One Python feature I love is how easy it is to create custom context managers.
They let you wrap setup and cleanup logic into a clean, reusable abstraction.
Useful for things like database connections, transactions, file handling, locks, temporary resources, and more.
Prashant retweeted
"We're smart enough to invent AI, dumb enough to need it, and stupid enough to not know if we did the right thing."
- Jerry Seinfeld
Prashant retweeted
I'll be sharing my screen this Friday to help you understand how you can build your first AI agent using Google's ADK.
I'll do it at 10 am EST.
This is a free Google Meet that anyone can join.
I hope the session to be around 1 hour, but I know it will go for 2 - 3 hours like it always does.
Here is the plan:
1. I'll pull up my Visual Studio Code
2. I'll show you how to build a pipeline to process a bunch of files and embed them in a local vector store.
3. I'll then show you how to create a simple RAG Agent using Google's ADK.
4. Finally, we'll build another pipeline that uses the agent to answer questions.
If you want to join, you can use the Google Meet link below.
Prashant retweeted

OpenAI@OpenAI7 Aug 2025
🇺🇸
United StatesConnected via WebAccount-level information, not a live location or per-post device.
GPT-5 is here.
Rolling out to everyone starting today.
openai.com/gpt-5/
Introducing GPT-5
Prashant retweeted
Variables Behavior in Mojo 🔥
I've been exploring Mojo lately and here is how the variables generally work.
↓
Prashant retweeted
PSA: Don't let any Google docs setting be: "Anyone on the internet with the link can view", they're scraping these docs for AI.
Readers added context they thought people might want to know
A representative for Google confirmed to Business Insider that simply changing the share settings to "anyone with the link" did not mean that a document was "public" and would be used for AI training.
businessinsider.com/google-docs-pu…
Prashant retweeted
Generating reproducible outputs in OpenAI models.
A common challenge encountered when using GPT models in applications is the lack of determinism in certain situations.
If you seek deterministic outputs from GPT models, here's a useful trick to consider:
↓
Prashant retweeted

OpenAI@OpenAI22 Aug 2023
🇺🇸
United StatesConnected via WebAccount-level information, not a live location or per-post device.
We've just launched fine-tuning for GPT-3.5 Turbo! Fine-tuning lets you train the model on your company's data and run it at scale. Early tests have shown that fine-tuned GPT-3.5 Turbo can match or exceed GPT-4 on narrow tasks: openai.com/blog/gpt-3-5-turb…
Prashant retweeted
🚨 Space Alert 🚨
Join us for a space on "Growth of Developers in the Age of AI"
We have very special guests .
@wahVinci
& .
@capeandcode
🗓️ 22nd May
🕗 6 PM (IST)
Get strategies to amplify your skills and advance your career through the power of AI!
Don't miss out! 💫
Prashant retweeted
Replying to @ylecun
If you measure things by number of questions on Stack Overflow, you are measuring them by amount of confusion, not popularity. 😂
Prashant retweeted
I'm not a religious person, but I do believe there are profound teachings to be found in the New Testament and the Gita
Prashant retweeted
When you want to present your Machine Learning Solution in various hackathons or POCs in significantly less time, with fewer lines of code and nice looking UI.
Here is a better idea instead of setting your solution in a notebook, Streamlit helps in a pretty good way with python.
Prashant retweeted
Meet other AssemblyAI Creators:
@thedataprof
@marlene_zw
@DanKornas
@aiflavours
@Sumanth_077
@1littlecoder
@capeandcode
@andfanilo
@misraturp
@r_o_connor
@python_engineer
Learn more about it and how you can apply:
assemblyai.com/blog/introduc…
Prashant retweeted
‣ AUC-ROC curves are crucial in deciding the threshold part for binary classification problems.
‣ In most cases, we take a 0.5 score as the threshold
‣ But what if I told you that there is a mechanism that is used to select the best threshold
Concepts and Visualization🧵
Prashant retweeted
Are you interested in recommender systems, in particular, about argument-based recommender systems?
In this thread🧵 I explain in brief what they are, what are their data sources and, what are their main goals and challenges.
English version: xitter.cf/SeguraAndres7/status/1…
1/2
Have you heard about argument-based recommender systems?
Do you like to receive explained and argued recommendations?
🚨SPOILER ALERT🚨: my research is about it.
@RedDivulga @CrueUniversidad @UAM_Madrid @UCCUAM @EDoctorado_UAM
I open #HiloTesis 👇
Prashant retweeted
Unified Analytics in Spark ⭐️
• One of the major selling points is the unification principle in Apache Spark.
• It is a core component of Spark's design philosophy and is available in Python, R, Java and Scala,
let's talk about it
↓
Prashant retweeted
This is an opportunity to get early into something awesome... 🤫
I've been using @oo_circles for a couple of weeks now and you've probably seen my videos.
Circles has a great potential to become a video platform for educational content. And they are looking for beta users!
👇
Prashant retweeted
Proud to have another great creator join the community on @oo_circles
Explaining Precision and Recall intuitively.
So I created a video on @oo_circles trying to explain both the concepts with an example.
Would love some feedback!






















