Azizkhani

Software Engineer | Java

[Azizkhani @azizkhani]

@amirarianarjmnd معمارش قطعا رزیدنت اویل زیاد بازی میکرده

[Mehdi Allahyari @MehdiAllahyari]

ساخت یک LLM از صفر!

اگر می‌خواهید بدانید واقعاً در دل مدل‌های زبانی چه می‌گذرد، این ویدیو فوق‌العاده است. طرف، از مفاهیم پایه مثل شبکه‌های عصبی و توکنایزیشن شروع می‌کند و تا معماری ترنسفورمرها پیش می‌رود. نکته جذاب اینجاست که همه چیز با کد واقعی و از صفر پیاده‌سازی شده است.

در این ویدیو به این مباحث کلیدی پرداخته شده است:
• درک عمیق چت‌بات‌ها و نحوه کارکرد آن‌ها
• بررسی شبکه‌های عصبی (Neural Networks)
• نحوه عملکرد توکنایزیشن و Embeddingها
• تشریح معماری ترنسفورمرها (Transformers)
• ارائه کانتکست تاریخی و تکامل این تکنولوژی

این ویدیو برای کسانی که می‌خواهند از سطح تئوری فراتر بروند و پیاده‌سازی واقعی یک ایجنت یا مدل زبانی را ببینند، عالی است.

کد پروژه:
https://t.co/eS6Hcb8qld

لینک ویدیو:
https://t.co/mZdxNII4KB
کانال تلگرام: https://t.co/wW5jwFBTIS

[Gratomic AI Bot | هوش مصنوعی گراتومیک @GratomicAi]

مصاحبه‌ای تکان‌دهنده با داریو آمودی، خالق Claude AI و مدیرعامل Anthropic؛
آمودی:
«ابتدا کدنویسی ناپدید می‌شود، سپس بقیه مهندسی نرم‌افزار»

«مصنوعی قرار است در بسیاری از کارها از شما بهتر باشد»

ما در آنتروپیک روز و شب کد می‌نویسیم. این واقعیت ساده، باعث شد تا ابزاری داخلی به نام ClaudeCode بسازیم. از آنجا که ما خودمان توسعه‌دهنده‌ایم، بینش و نگاهی کاملاً منحصربه‌فرد از درون به این ماجرا داریم که...
1/9

[Azizkhani @azizkhani]

@ErfanManavi عکس ساختمونه ، کنگان ۳ 😂

[Azizkhani @azizkhani]

😂😂😂😂😂

[Massimo @Rainmaker1973]

The girl was too worried that her parents overslept, so she decided to take a drastic action.

[Gratomic AI Bot | هوش مصنوعی گراتومیک @GratomicAi]

از اصطلاحات رایج و حرفه ای AI چه میدانیم؟

در اینجا ما فهرست جامع اصطلاحات استراتژیک هوش مصنوعی را گرد آورده ایم؛

بطور مثال AGI چیست و چطور تغییر بنیادین در جهان انسان ها ایجاد خواهد کرد؟

در ادامه:...
1/40

[Aurimas Griciūnas @Aurimas_Gr]

I have been building and operating Agentic AI Systems for the past few years and the same patterns keep emerging. 👇

𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗗𝗿𝗶𝘃𝗲𝗻 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 is the most reliable way to be successful in building your 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗦𝘆𝘀𝘁𝗲𝗺𝘀 and continue improving them - here is my template.

Let’s zoom in:

𝟭. Define a problem you want to solve: is GenAI even needed?
𝟮. Build a Prototype: figure out if the solution is feasible.
𝟯. Define Performance Metrics: you must have output metrics defined for how you will measure success of your application.
𝟰. Define Evals: split the above into smaller input metrics that can move the key metrics forward. Decompose them into tasks that could be automated and move the given input metrics. Define Evals for each. Store the Evals in your Observability Platform.

ℹ️ Steps 𝟭. - 𝟰. are where AI Product Managers can help, but can also be handled by AI Engineers.

𝟱. Build a PoC: it can be simple (excel sheet) or more complex (user facing UI). Regardless of what it is, expose it to the users for feedback as soon as possible.
𝟲. Instrument your application: gather traces and human feedback and store it in an Observability Platform next to previously stored Evals.
𝟳. Run Evals on traced data: traces contain inputs and outputs of your application, run evals on top of them.
𝟴. Analyse Failing Evals and negative user feedback: this data is gold as it specifically pinpoints where the Agentic System needs improvement.
𝟵. Use data from the previous step to improve your application - prompt engineer, improve AI system topology, finetune models etc. Make sure that the changes move Evals into the right direction.
𝟭𝟬. Build and expose the improved application to the users.
𝟭𝟭. Monitor the application in production: this comes out of the box - you have implemented evaluations and traces for development purposes, they can be reused for monitoring. Configure specific alerting thresholds and enjoy the peace of mind.

✅ 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗼𝗳 𝘆𝗼𝘂𝗿 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻:

➡️ Run steps 𝟲. - 𝟭𝟬. to continuously improve and evolve your application.
➡️ As you build up in complexity, new requirements can be added to the same application, this includes running steps 𝟭. - 𝟱. and attaching the new logic as routes to your Agentic System.
➡️ You start off with a simple Chatbot and add a route that can classify user intent to take action (e.g. add items to a shopping cart).

Learn all of the practices of Eval Driven Development Hands-on in my End-to-end AI Engineering Bootcamp: https://t.co/gWBu8OLTzn

🎁 Grab your 15% discount by applying code KICKOFF15 at the check-out.

What is your experience in evolving Agentic Systems? Let me know in the comments 👇

[Akshay 🚀 @akshay_pachaar]

Google open-sourced MCP Toolbox for Databases.

I gave it access to everything else.

For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol

However, most enterprise knowledge doesn't actually live in databases.

It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs.

So Agents can't see any of it, which means they're working with a fraction of the context they need.

I fixed that using MindsDB.

It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured.

This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax.

The clever part is how it connects to the MCP Toolbox.

MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back.

It doesn't know or care that the data came from five different sources behind the scenes.

This setup unlocks some powerful capabilities:

→ One SQL interface for dozens of enterprise sources
→ Cross-datasource joins (combine GitHub and CRM data in a single query)
→ Built-in ML capabilities for working with unstructured data
→ Simple MCP tools that now have massively expanded reach

In the video below, the Agent queries GitHub data and a customer review database in one SQL query.

So what used to require ETL pipelines and weeks of engineering effort now happens instantly.

At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with.

I have shared the GitHub repo in the replies, where you can find more details about this.

[Santiago @svpino]

Anthropic launched MCP Apps this week.

This enables a new class of applications using Generative UI.

Here is the thing:

Chatbots are dumb. You can't build a serious application for humans without these:

• Progress indicators
• Status updates
• Confirmations

UX is still important, and this new wave of "everything is a chatbot" is learning this lesson the hard way.

Generative UI will be the next big thing.

Agents must be part of the UI, not just the conversation.

People don't want to read a dump of text responses. Instead, we want agents to drive cards, tables, forms, progress indicators, and confirmation dialogs.

The agent decides intent. Your application will render it visually.

Think about it this way:

1. Your agent will express what UI should exist
2. Your frontend will decide how to render it

Here's how the pieces fit together:

1. The A2UI and MCP-UI specifications define what an agent wants to show. They're declarative descriptions of components, interactions, and how user input flows back to the agent.

2. AG-UI is the transport layer. It handles streaming updates, shared state between agent and frontend, tool calls, and bidirectional communication.

3. Your app still controls everything that matters: rendering, UX, permissions, safety.

This is the future of agentic applications.

[Azizkhani @azizkhani]

@AminP82 @reza2fta 😁😁😁

[Azizkhani @azizkhani]

خدایا شکرت چه بارونی میاد 🙏🏻🤲

[Von Datawarehausen @urgauovmi]

از من به شما نصیحت، مدل‌ها میان و میرن، به کانسپت‌ها و پاردایم‌ها بچسبید!

[Azizkhani @azizkhani]

@atorabi76 این کچله که دلال ماشین بود اینجا چیکار میکنه

[Azizkhani @azizkhani]

@NVIDIAGeForce GeForce Day

[Azizkhani @azizkhani]

@ErfanHUD نوا

[بابک.. @babakm1912a2510]

سن تغییر می‌کند، اما عشق مادر تغییر نمی‌کند. ‌)))

[Azizkhani @azizkhani]

@farhad_fathi_ir تو مجسمه چی هستی؟

[Azizkhani @azizkhani]

@a__amirhossein ای روزگار 😂

[Jacky Chan @linux_china]

new JWT Filter with Java 25 Scope Values.