Ruli(alip)

Technologist | Software Engineer

[Ruli(alip) @alifRuliarso]

AI Engineering Skills map for software engineering fundamentals.

[Andrew Ng @AndrewYNg]

How have software engineering fundamentals changed with agentic coding? Here is our AI Engineering Skills map for software engineering fundamentals. https://t.co/cnRLj43DLs

[Ruli(alip) @alifRuliarso]

Benchmark for coding agent

[MiniMax (official) @MiniMax_AI]

🐙 Introducing OctoCodingBench, a new benchmark for aligned coding agents: https://t.co/oKaF7jjagb

Passing tests ≠ aligned behavior. An agent can produce code that aces every unit test while ignoring system guidelines, violating project conventions, or misusing tools.

In real-world coding, how you solve matters as much as what you solve. Nobody wants an agent that ships perfect code while deleting your README, reformatting every file, and mass-commenting in LLM-ese.

Don't let your coding agent paperclip-max your repo!

[Ruli(alip) @alifRuliarso]

Bonus fast request #trae #codingagent

[TRAE @Trae_ai]

TRAE's anniversary is coming up on 1/20!

Here's our gift for you: Limited-time Bonus Fast Requests 🎁

1️⃣ Free users get 600 bonus Fast Requests, valid through 02:00 UTC, February 14, 2026.
2️⃣ Pro users get 800 bonus Fast Requests, valid through 02:00 UTC, March 14, 2026.

All models can be accessed by applying the bonus during this period.

Happy Building with TRAE!
Claim here: https://t.co/FOs48xEd6Q

[Ruli(alip) @alifRuliarso]

A Zero-Code Multi-Agent Platform for Developing Everything

[OpenBMB @OpenBMB]

🚀 ChatDev 2.0 Levels Up! Forget rigid workflows—build your own multi-agent teams for any task with a simple "Drag + Configure" interface.
🔗 Start it now: https://t.co/oOc8pRXU8j

✨ Visual & Zero-Code: Stop choosing between ease and power. We use a "Drag + Configure" paradigm that abstracts complex coding into an infinite canvas. Simply drag to link nodes and use form-based configs to fine-tune prompts, models, and contexts without writing a single line of code.

🧠 Unbound Orchestration: Break free from linear pipelines. Our robust graph structure natively supports loops (e.g., self-reflection) and infinite nesting (e.g., subgraphs) to scale complexity. We uniquely decouple control flow from data flow, allowing for precise logic branching, data cleaning, and parallel distribution.

🌌 Limitless Potential: Whether you are a novice or a geek, we have you covered. Start instantly with built-in templates for 3D Modeling, Game Dev, and Deep Research. Developers can dive deeper with full open-source access to customize nodes, integrate private LLMs, and refactor memory backends.

#AI #OpenSource #LLM #AgenticAI #Agent #MultiAgent #ChatDev #OpenBMB

[Ruli(alip) @alifRuliarso]

Modern LLMs generate patterns, not principles. Dignified Python gives agents the intent they lack, ensuring code is explicit, consistent, and engineered with care. Here are ten rules from our Claude prompt.

[colton @coltonpadden]

Looking for rules to add to your Claude prompt for Python development?

This blog post shares 10 rules we use while developing @dagster, and at the end of the post we include our full prompt!

https://t.co/dmMd6TAnC5

[Ruli(alip) @alifRuliarso]

Zero hidden fee #transfer

[Ogvio @OgvioGlobal]

2026 = smarter money habits.

Keeping part of your balance in USD/EUR-pegged value on Ogvio can help reduce currency volatility 💵

Create an Ogvio account and protect the value of your money! 👉 https://t.co/V0xrLibPpe

[Ruli(alip) @alifRuliarso]

Learn software design basic

[freeCodeCamp.org @freeCodeCamp]

When you're writing code, you need to think about designing systems that are scalable and maintainable.

And inefficient software design can lead to issues like scope creep, miscommunication, delays, and so on.

In this guide, Soham teaches you Software Design basics along with some helpful best practices to follow.

https://t.co/X4xpKkQvO5

[Ruli(alip) @alifRuliarso]

Deploy directly inside #TRAE SOLO

[TRAE @Trae_ai]

Vibe coding is fun.
Shipping is where most projects get stuck.

We made a short tutorial showing how to take a vibe coding idea → production-ready app with TRAE SOLO.

Let SOLO run end-to-end, deploy instantly, then layer in:
- user authentication
- database storage
- payments service
- LLM integrations

You can bring yours ideas to life fast in TRAE SOLO.

[Kilo (acq. by Anaconda) @kilocode]

Spectre = Devstral 2: Mistral AI Makes 2 Models Free All December for Kilo Users

Mistral just launched Devstral 2 and Devstral Small.

Our stealth model (Spectre) was a pre-release version of Devstral all along.

Both models (Devstral 2 and Devstral Small 2) will be free for all of December on Kilo Code.

Learn more: https://t.co/nMkPOwAjOt

[OpenAGI Labs @agiopen_org]

Website: https://t.co/VDdb6KYJ0X
SDK: https://t.co/ihQxypjouZ
Blog post: https://t.co/j8cXvrpI24

The number of use cases is endless: software QA agents, e-commerce agents, social media management agents, data entry, bulk operations, etc. You can build whatever you want!

[The New Stack @thenewstack]

Vector search alone isn’t enough. Production-grade AI search needs more: combining semantic, keyword and metadata retrieval, applying machine-learned ranking and handling constantly changing structured and unstructured data, all at scale.

Thanks to @vespaengine
https://t.co/4jDhXoaBKc

[Ruli(alip) @alifRuliarso]

API Security

[freeCodeCamp.org @freeCodeCamp]

When you're building apps, it's a good practice to bake security into the whole process.

And that's what you'll learn how to do in this DevSecOps + API security course.

It covers common vulnerabilities, why API security matters, key principles of DevSecOps, and more.

https://t.co/hjzlCmlZCa

[Ruli(alip) @alifRuliarso]

Elon Musk Gratiskan Layanan Starlink untuk Warga Terdampak Banjir di Sumut https://t.co/fW54i0OEPK

[Ruli(alip) @alifRuliarso]

Building AI agent

[Philipp Schmid @_philschmid]

Learn how to build your own AI agent from scratch with Gemini 3 Pro. Excited to share this practical guide designed for everyone starting from simple text generation to a functioning CLI Agent.

- Construct a working prototype in under 100 lines of code.
- Start from basic text generation using the Gemini 3 Pro model.
- Define function capabilities using JSON schemas.
- Build a logic loop to intercept and execute tool calls.
- Assemble components into a functional multi-turn CLI application.
- Learn Best Practices for Engineering Agents

Very proud and excited to share this! 🤗

[Ruli(alip) @alifRuliarso]

E-ink Vocabulary Card E2 Fits Language Learning Into a Gum Pack https://t.co/Ok9rS0oSRY via @yankodesign

[Ruli(alip) @alifRuliarso]

Gemini 3

[GitHub @github]

Gemini 3 Pro is now in public preview for GitHub Copilot! Early testing in @code shows a 35% higher accuracy compared to Gemini 2.5 Pro. 🚀

Solve real-world problems faster and more effectively. Learn more. 👇
https://t.co/kdQp5OihEa

[Ruli(alip) @alifRuliarso]

Gemini 3

[Kilo (acq. by Anaconda) @kilocode]

We tested Gemini 3 Pro Preview on 5 hard coding/UI tasks against Claude 4.5 Sonnet and GPT‑5.1 Codex.

Scores (our internal rubric):
• Gemini 3 Pro: 72%
• Claude 4.5 Sonnet: 54%
• GPT���5.1 Codex: 18%

What stood out about Gemini 3 Pro:

• Code feels human: sensible libraries, efficient patterns, minimal prompting.
• Designs are adaptive, not cookie‑cutter
• Consistently correct CDN paths and awareness of newer tools/architectures.

Let's dive deeper.

[Ruli(alip) @alifRuliarso]

Gemini 3

[Cline @cline]

We've been testing Gemini 3 for the past few weeks, and here's what stands out:

It's faster, the tool calling is sharper, and the UI taste is finally dialed in.

In this test, we gave Gemini 3 (left side) and Gemini 2.5 (right side) the same tasks and see the difference in the results.

[piet @repiet]

@cursor_ai The wheels on the bus go round and round

[Ruli(alip) @alifRuliarso]

Kafka diagnostics tools
#Kafka

[SoftwareMill @softwaremill]

We are thrilled to announce we are building KafkaPilot, a proactive tool designed to diagnose and resolve common issues in Apache Kafka.

💡 KafkaPilot explained

We are starting with 17 scenarios covering typical configuration, availability, and performance faults (find the GitHub link at the end of the post).

Want to know more about the idea and how KafkaPilot can save you valuable time? @grajo, Staff Software Engineer at SoftwareMill, shares the full story on our blog!

🔗 You can read it here: https://t.co/CtseBNii3W

📥 We need your feedback

KafkaPilot is in its early stages of development. For it to become a truly essential tool, we need the most crucial factor: input from the community!

What are your most common Kafka pain points? Tell us what keeps you up at night and help us create a tool that will truly make your work easier in the future.

The easiest way to contribute?

🔗 Take our quick, 1-minute survey! https://t.co/XzzPuGQUkI

Thank you!

And here you will find all 17 KafkaPilot scenarios: https://t.co/ImqJTmENRu

#KafkaPilot #ApacheKafka #Kafka #DevTools