Ahmed M. AlShafiy

[ViralRush ⚡ @ViralRushX]

The Black Hornet Nano is one of the smallest military drones, tiny and quiet enough to be called the ‘mosquito drone.’

[Ahmed M. AlShafiy @AAlShafiy]

@flynas @flynascare تم اعادة جدولة رحلتي رقم XY16 بتارخ 09/03/2026
من الساعة 2 الي الساعة 4
وغيرت رحلتي الي تاريخ 10/03/2026
رقم XY54
لم اجد حقيبتي .. ذهبت لمكتب الامتعة في مطار جدة مرتين وافادوا انها وصلت الرياض و في مطار الرياض لم اجدها ورفض الموظف تسجيل يلاغ لاختلاف الرحلة

[Ahmed M. AlShafiy @AAlShafiy]

@ibrahimmwageeh Template

[Ahmed M. AlShafiy @AAlShafiy]

@ai_uncovered File

[Shubham Saboo @Saboo_Shubham_]

AI Agents collapse when given access to hundreds of tools at once.

This unified MCP server uses progressive discovery to guide AI Agents through 1000s of tools instead of loading everything upfront.

100% Opensource.

[Ahmed M. AlShafiy @AAlShafiy]

https://t.co/rjCMquSee4

[Ahmed M. AlShafiy @AAlShafiy]

@noway2330 الحمدلله والشكر لله

[Matt Dancho (Business Science) @mdancho84]

Stop Prompting LLMs.
Start Programming LLMs.

Introducing DSPy by Stanford NLP.

This is why you need to learn it:

[Ahmed M. AlShafiy @AAlShafiy]

@noway2330 الحمدلله

[Ahmed M. AlShafiy @AAlShafiy]

@noway2330 على فاصل دقيقه اظن فيه لغم

[Ahmed M. AlShafiy @AAlShafiy]

@noway2330 الحمدلله

[Ahmed M. AlShafiy @AAlShafiy]

@noway2330 VEEE ..

[Ahmed M. AlShafiy @AAlShafiy]

@noway2330

[Ronald van Loon @Ronald_vanLoon]

#GenerativeAI Tech Stack 2025
by @Python_Dv

#MachineLearning #ArtificialIntelligence #ML #MI #LLM

cc: @bernardmarr @evankirstel @miketamir

[Ahmed M. AlShafiy @AAlShafiy]

https://t.co/mvGYctkBBv

[Michael Bargury @mbrg0]

we hijacked microsoft's copilot studio agents and got them to spill out their private knowledge, reveal their tools and let us use them to dump full crm records

these are autonomous agents.. no human in the loop

#DEFCON #BHUSA @tamirishaysh

[steve hsu @hsu_steve]

Is Chain-of-Thought Reasoning of LLMs a Mirage?

... Our results reveal that CoT reasoning is a brittle mirage that vanishes when it is pushed beyond training distributions. This work offers a deeper understanding of why and when CoT reasoning fails, emphasizing the ongoing challenge of achieving genuine and generalizable reasoning.

... Our findings reveal that CoT reasoning works effectively when applied to in-distribution or near
in-distribution data but becomes fragile and prone to failure even under moderate distribution shifts.
In some cases, LLMs generate fluent yet logically inconsistent reasoning steps. The results suggest that what appears to be structured reasoning can be a mirage, emerging from memorized or interpolated patterns in the training data rather than logical inference.

... Together, these findings suggest that LLMs are not principled reasoners but rather sophisticated simulators of reasoning-like text.

[Ahmed M. AlShafiy @AAlShafiy]

@stockplaymaker1 1

[Avi Chawla @_avichawla]

A RAG engine for deep document understanding!

RAGFlow lets you build enterprise-grade RAG workflows on complex docs with well-founded citations.

Supports multimodal data understanding, web search, deep research, etc.

100% local & open-source with 55k+ stars!

[Ronald van Loon @Ronald_vanLoon]

Self-driving F1 car
by @RevolveNTNU

#SelfDrivingCars #AutonomousVehicles #AI #ArtificialIntelligence #Automotive

cc: @terenceleungsf @ylecun @chr1sa