bala baskar

Data Scientist

[Codez @0xCodez]

OpenAI just launched a 3-hour course on building agentic systems from scratch:

00:00 - Building workspace agents
37:42 - Deep dive into OpenAI AgentKit
1:24:01 - Agent memory (loops, context, evals)
2:21:44 - Agentic training (OpenAI playbook)

This 3-hour watch will replace you 10 paid agentic courses.

Watch it today, then learn how to build a team of AI agents from scratch in the article below.

[Matt Pocock @mattpocockuk]

My skills repo has 160K stars, 7.5m downloads...

...and no tutorial.

So, here it is. Watch me walk through the essential skills:

- /grill-with-docs
- /to-spec
- /to-tickets
- /implement
- /code-review

It's the whole flow, end-to-end. Enjoy:

[How To Prompt @HowToPrompt__]

Stanford + Meta just dropped the paper that flips everything about AI agents.

It's called "Code as Agent Harness."

Right now, we treat large language models as text generators. When they need to solve a complex problem, they rely on a "chain of thought."

But natural language is slippery. It's vague. It loses context. When an agent hallucinates in English, it just keeps talking.

So they introduced a framework that changes the entire architecture of autonomy: "Code as Agent Harness."

They stopped asking the AI to reason in words, and forced it to reason in code.

Code isn't just the final output anymore. It is the memory. It is the environment. It is the boundary.

Instead of writing a paragraph about how to solve a problem, the agent writes a script, executes it, and reads the output.

Tests become its senses. Execution logs become its memory. Sandboxes become its physics.

If an agent makes a mistake in English, it apologizes and hallucinates again.

If an agent makes a mistake in code, the compiler throws an error. The trace tells it exactly what broke. The system forces it to fix it.

This is where prompt engineering dies, and systems engineering takes over.

The paper proves that reliability doesn't come from a smarter base model. It comes from the "harness" wrapped around it:

- The model proposes.
- The harness executes.
- The environment returns feedback.
- The verifier checks.

[monokern @monokern]

Nobody will see this but this is how I do research 10x faster now

> I drop a topic into Claude Code
> It finds 10 relevant YouTube sources automatically
> Sends them to NotebookLM

6 minutes later I get a full structured analysis, an infographic, and a markdown file saved to my vault

Before this I was spending 3 hours doing the same thing manually and ending up with messy notes I'd never look at again

Now the system does it in one command and the output gets better every time I use it

full setup guide in the article

[東大AI研究会 @todai_aiken]

【Google ColabだけでLLMを0から作る】
「EveryonesLLM」を公開しました🔥
Google Colabだけで、0.5Bサイズの本格的なLLM/SLMをフルスクラッチで作る教材です。

600問以上の穴埋めを解きながら、実装して、学習して、最後は会話できるモデルまで育てます。

ちょっと大変ですが、自分が作ったAIと話す朝は格別です😁
https://t.co/hEgqkto3dx

<謝辞>
本プロジェクト「EveryonesLLM」は、株式会社NTTデータMSE様のご支援のもと、学生団体「東大AI 研究会」によるOSSプロジェクトとして完成しました。 本教材の作成にあたり、温かいご支援とご協力をいただいた株式会社NTTデータMSE様に、心より感謝申し上げます。

[Dan Kornas @DanKornas]

Stop learning ML math from random tabs.

Mathematics for Machine Learning is a curated GitHub collection of books, papers, video lectures, and math basics for learning and reviewing the math behind machine learning.

It helps you build a stronger foundation by grouping reliable resources around the concepts ML engineers keep running into: linear algebra, calculus, probability, statistics, information theory, matrix calculus, and deep learning math.

Key features:

• Books first – points to Mathematics for Machine Learning, Deep Learning math basics, Probabilistic ML, Bayesian modeling, and deep learning math references
• Papers included – links focused reads like matrix calculus for deep learning and an overview of mathematics in AI
• Video lecture paths – includes multivariate calculus, linear algebra, and CS229 lecture playlists
• Math basics section – collects statistics, probability, information theory, linear algebra, and calculus primers
• Short notes per resource – each entry gives context so you can decide what to open next

Free public GitHub repo.

Link in the reply 👇

[Dhruv @dhruvtwt_]

Why is no one talking about this?

@nvidia is offering around 80 AI models via hosted APIs absolutely for free.

You get access to MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek 3.2, GPT-OSS-120B, Sarvam-M etc.

This plugs straight into OpenClaude, OpenCode, Zed IDE, Hermes agent and even with Cursor IDE.

Setup:
– Grab API key: https://t.co/Wfdclm0hY2
– base_url = "https://t.co/VOGC10LmGP"
– api_key = "$NVIDIA_API_KEY"
– select model (e.g. minimaxai/minimax-m2.7)

If you’re building or experimenting, this is basically free inference.

Lock in and start building today anon.

Thank me later.

[Dataibridge @Dataibridge_01]

ローカルLLMを全く触ったことがない人を対象に、Kaggle自然言語処理コンペで最低限必要なLLM活用の入り口を丁寧に解説。

環境構築から基本的な使い方まで、社内勉強会レベルの実践的入門資料。

・ローカルLLMの環境構築と基本操作（触ったことない人向け超入門）
・Kaggle NLPコンペでLLMをどう活用するかの具体的な考え方と最低限の知識
・実務やコンペで即座に試せる、LLM導入の第一歩となる実践Tips

ハードルが高いと感じていた人が一気にKaggle LLM活用の世界に入れる、親切設計の神入門スライドです！

https://t.co/BkICdRc41O

[alphaXiv @askalphaxiv]

The best way to learn frontier research is to replicate it yourself.

And now, you can also win prizes for that!

We are excited to announce our partnership with @marimo_io for a competition to bring research to life.

All you have to do is pick a paper, build a marimo notebook that brings the core idea to life, and experiment with the research topic.

Prizes: Mac Mini + $500! 👀
Deadline: April 26, 11:59 PM PST
Individual and team submissions are all welcome
Full details found below 👇

[bala baskar @bala_theQuant]

@hengcherkeng I'm still trying to set a boundary between what I should do and what I should delegate to an AI coding agent to maximize the results.

[bala baskar @bala_theQuant]

@kaggle getting 404 not found error this morning. Any issue with the website?

[Shruti @heyshrutimishra]

NVIDIA just released FREE online courses in AI.

Here are 9 courses you can't afford to miss:

[Bishal Nandi @LearnWithBishal]

Harvard University just released free online courses.

No payment is required.

Here are 12 courses you don't want to miss in 2024:

[Richard McElreath 🐈‍⬛ @rlmcelreath]

Want to learn a little game theory? Lectures from my course "Very Little Evolutionary Game Theory". Topics:
1. Evolution of Conflict
2. Evol of Cooperation
3. Evol of Relationships
4. Evol of Families
5. Evol of Societies
What at x2 speed for full effect: https://t.co/fOc5oKzh5w

[Mathieu @miniapeur]

What are some examples of outstanding PhD theses in the field of machine learning?

[DAIR.AI @dair_ai]

Top ML Papers of the Week (June 19 - 25):

- RoboCat
- LMFlow
- AudioPaLM
- ClinicalGPT
- SequenceMatch
- Textbooks Are All You Need
...

[Eyisha Zyer @eyishazyer]

AI is shaping the future of our world.

Google, IBM, Microsoft are Investing Billions into AI.

9 Courses to Make Your Space into It. All FREE

[Santiago @svpino]

I found a page listing 135 different Machine Learning algorithms.

No wonder most people new to the field have no idea where to start, yet experts do this almost effortlessly.

Here is how they do it every day:

[Madza 👨‍💻⚡ @madzadev]

7 YouTube channels to boost your productivity and personal growth (do more in less time):

[bala baskar @bala_theQuant]

@__mharrison__ %%writefile - command to convert any code block to python code file