Mohammed Rami Benhamida

💻 Full Stack Developer
📱Flutter Developer
🎨 UI/UX Designer

[Marco Ramilli @Marco_Ramilli]

🤖 matryca-plumber
⭐ 45 stars

Turn your Logseq notes into a secure, agentic workspace. Let Claude and Cursor query your second brain locally via MCP with zero data leaks.

🔗 https://t.co/pJhjnwZPGU

#AI #MachineLearning

[Akshay 🚀 @akshay_pachaar]

The easiest way to find out which models you can run on your computer:

1) Install
npm install -g llm-checker

2) Detect your hardware
llm-checker hw-detect

3) Get recommendations by category
llm-checker recommend --category coding

Credits to @svpino for bringing this to my attention. I found it super useful and thought of sharing it with you all.

Here are some of the recommendations I got:

[0xMarioNawfal @RoundtableSpace]

A FULLY FREE CODING AGENT JUST DROPPED - DEEPSEEK V4 PRO, KIMI K2.6, MINIMAX M2.7, ALL FREE, ONE INSTALL.

THE PAID CODING AGENT ERA HAS A PROBLEM.

[Tom Dörr @tom_doerr]

Converts research papers into editable diagrams and slides

https://t.co/pRfnjfIXxT

[DeepTechTR 🇹🇷 @DeepTechTR]

🚨 Arkadaşlar, web scraping dünyasında çok ciddi bir kırılma noktası yaşandı. 🫪

OpenClaw (Scrapling), artık herhangi bir web sitesini **engellenmeden** scrape edebiliyor.

- Sıfır robot tespiti
- Cloudflare’ı doğal yollarla bypass ediyor
- BeautifulSoup’tan **774 kat daha hızlı**
- Seçici (selector) bakımına gerek yok
- Sadece veri istiyorsunuz, gerisini o hallediyor

Tamamen açık kaynak ve son derece güçlü.

Web scraping, veri toplama ve otomasyon işleriyle uğraşan herkesin mutlaka incelemesi gereken bir proje.

🔗 GitHub: https://t.co/XqGgrlerdW

Sizce bu tür stealth ve yüksek performanslı scraping araçları, veri toplama ve otomasyon süreçlerini ne ölçüde dönüştürecek?

Düşüncelerinizi yorumlara yazın, beraber konuşalım. 🕷️

[shmidt @shmidtqq]

https://t.co/zqxxSvkxcg

[Shruti Codes @Shruti_0810]

Academic research just got automated.

This open-source CLI does in seconds what PhDs take hours to do.

Feynman:

→ Ask a question
→ 4 AI agents take over

• Researcher → pulls real papers + repos
• Reviewer → simulates peer review (with scores)
• Writer → turns chaos into clean output
• Verifier → checks every source (kills dead links)

It even cross-checks studies with their code to catch fake claims 🤯

No cloud.
No cost.
No excuses.

GitHub ↓
https://t.co/yTaS4Q9Ob8⁠�

[Aakash Verma @VermaAakash3]

Guess what? A Russian guy has found a way to learn anything ten times faster using AI!

It all comes down to NotebookLM, Gemini, and Obsidian.

[Economy news | Bitcoin | AI @cryp2_]

🚨جوجل تكشف نظاماً يكتب أبحاثاً علمية كاملة... خلال 40 دقيقة تحول دفتر ملاحظاتك الى بحث علمي

أطلقت Google نظام PaperOrchestra الذي يستخدم عدة وكلاء ذكاء اصطناعي لكتابة أبحاث جاهزة للنشر بدءاً من الفكرة والبيانات، مع توليد المراجع والرسوم ومراجعة ذاتية تحاكي التحكيم العلمي.

[alphaXiv @askalphaxiv]

"PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing"

This paper builds a multi-agent system for AI research writing.

Each part of it handles one job: one plans, one does literature search, one makes figures, one writes, and one revises.

This treats paper writing like orchestration, not autocomplete.

They also introduce a benchmark built from 200 top AI papers, and show large gains over prior automated baselines, especially on literature review quality.

[Mohammed Ashour @Dr_Ashour93]

🚀 لطلاب الدكتوراه:

وجدت 10 أوراق علمية كنت أبحث عنها خلال 10 ثوانٍ فقط!

الطريقة:
1️⃣ استخدمت Moara
2️⃣ كتبت وصف دقيق لما أريده
3️⃣ حصلت على 15 ورقة فقط
4️⃣ اخترت أفضل 10
5️⃣ استخرجت البيانات منها مباشرة
🎯 النتيجة: البحث + استخراج البيانات في أقل من دقيقة!

[Alvaro Cintas @dr_cintas]

You can now fine-tune Gemma 4 completely FREE 🤯

No GPU. No credit card. No coding knowledge required. Just a browser and 500+ models to choose from.

→ Open the Unsloth Colab notebook
→ Pick your model + dataset
→ Hit Start Training

[Akshay 🚀 @akshay_pachaar]

Another blow to Anthropic!

Devs built a free and better Claude Cowork alternative:

- 100% local
- voice-enabled
- works with any LLM
- MCP tool extensibility
- obsidian-compatible vault
- background agents & web search
- automatic knowledge graph creation

100% open-source.

[بدور @albdoor28]

كباحثة كان يأخذ مني 3-4 ساعات لقراءة الأوراق ومقارنتها…
اليوم مع Tabbit Browser أنهيها في 20 دقيقة فقط
أفتح البحث مباشرة في المتصفح و تحدث معه بدون
copy-paste
أداة غيرت طريقة تفكيري فعلاً

جربوها: https://t.co/u1UiVAmRiF

[Ben Dicken @BenjDicken]

*Finally* read through @samwhoo's blog on LLM quantization.

It's incredible.

For many (even in tech) the understanding of how LLMs work stops at the surface level. Sam is helping us all go deeper, digging into the interesting facets of how AI models truly work.

Read it!

[Faheem Ullah @Faheem_uh]

PhD Students – How to easily identify a research gap?

Follow these simple steps.

1. Go to https://t.co/8yorkrreey
2. Select Idea Spark from the left side menu
3. Enter your research topic e.g., AI for healthcare
4. You can specify the following

-Any dataset related to your research
-Any papers related to your research

5. You can also specify the balance of research gap

-Focus on novelty
-Focus on feasibility
-Focus on breadth
-Focus on depth

6. Once specification made, click on generate
7. @Novix_science will identify gaps

Go through each research gap.

Each gap is linked with relevant research papers

Explore these papers to validate the identified gap.

Try Novix today: https://t.co/8yorkrreey

[Tom Dörr @tom_doerr]

Reviews scientific manuscripts using Stanford writing course methodology

https://t.co/8HnxIIeool

[Dr Asma Jabeen @DrasmaJabeen1]

Artificial intelligence assisted Academic writing recommendations for ethical use

[Amit Shekhar @amitiitbhu]

Many of you read this article.

One of the topics I will be writing about next is this: Why we choose to divide by sqrt(d_k) instead of some other factor.

Understanding Math is the key. Let's keep learning.

X is a knowledge sharing platform.

[Daily Dose of Data Science @DailyDoseOfDS_]

Make RAG 32x memory efficient and 40x faster (explained with code):