Constantin Liculescu

I lost 95+ lbs, kept it off, now I help others do the same - realistic weight loss, escape emotional & stress eating, and maintenance

[Constantin Liculescu @Cl11089640]

I’m happy to share that my Skool community is now open:

https://t.co/Mu8vWcepKA

It’s called Weight Loss and Maintenance - Real Help for Real Life.

I built it for people who want to lose weight in a realistic way and, just as importantly, learn how to keep it off. Not another short burst of motivation, perfection, or starting over every Monday. The focus is on better habits, better thinking, and stronger maintenance skills for real life.

Inside, I’ll be sharing practical help for cravings, emotional eating, stress eating, setbacks, eating out, holidays, and the mental side of staying on track. There will also be group coaching, useful resources, and more courses over time.

If you want a calmer, more solid, more sustainable approach to weight loss and maintenance, you’re very welcome inside.

[DeepLearning.AI @DeepLearningAI]

“Budget” and “financials” are different words, but embeddings understand they’re related.

That’s the foundation behind semantic search and one of the core building blocks of modern multimodal systems.

Learn how embeddings power retrieval across text, audio, images, and video in Building Multimodal Data Pipelines: https://t.co/fwbQKeiB7H

[Constantin Liculescu @Cl11089640]

OpenAI’s reported IPO push is more than a company milestone.

It would be a public-market test of the whole AI boom: huge demand, huge valuation, huge compute costs.

#OpenAI #AI #ArtificialIntelligence #IPO #TechNews

https://t.co/MDO0rpcDDF

[Stefan Đokić | .NET @TheCodeMan__]

Everyone is talking about MCP servers right now.
So I decided to create a realistic example in .NET and add it completely FREE to the:

My AI in .NET Starter Kit: https://t.co/8cOG2CgDfX

I built an MCP Server in .NET for API performance analysis.

Not a “hello world” demo.

A real example where GitHub Copilot Agent mode can actually call tools and analyze API performance for you.

You type something like: “Compare slow-thread-sleep with slow-task-delay using 20 users for 15 seconds”

And the MCP server:

→ Runs load tests
→ Compares endpoints
→ Measures p50/p95/p99 latency
→ Detects thread pool starvation
→ Suggests optimizations
→ Generates reports

The whole point was to show HOW MCP actually works in practice.

So instead of building another toy calculator example, I created a scenario around performance testing because it naturally fits the MCP model really well.

The project includes:

→ MCP Server in .NET
→ 10 MCP tools
→ Custom load testing engine in pure .NET
→ ASP. NET Core API with intentional performance issues
→ Blazor dashboard for visualizing results
→ Unit tests
→ Full source code

And yes, this is more educational than production-ready.

The goal is to help you understand:

→ How MCP servers expose tools
→ How AI agents call them
→ How tool orchestration works
→ How to structure an MCP server in .NET
→ How AI can interact with real developer workflows

I genuinely think MCP is going to become a very important skill for developers.

Especially for people building AI-powered tooling and developer platforms.
__

📌 Don't miss the next newsletter issue, 21,000 engineers will read it, join them: https://t.co/gI46R2Kc0c

♻️ Repost to others.
📂 You can save this post for later, and you should do it.

➕ Follow me to learn .NET and Architecture every day.

[Constantin Liculescu @Cl11089640]

@DeepLearningAI excellent training, I'm already applying it professionally and for my own projects

[Constantin Liculescu @Cl11089640]

Adult attachment styles can shape how we handle closeness, distance, reassurance, and independence. But they are not fixed identities. They are patterns, and patterns can become more visible, more flexible, and healthier.

#Psychology #AttachmentTheory #Relationships #InsightArea

https://t.co/4GMRyf0cUz

[Constantin Liculescu @Cl11089640]

@Jainadave_ quantic physics, of course

[Constantin Liculescu @Cl11089640]

OpenAI’s new ChatGPT personal finance features show where AI is heading next: not just answering general questions, but helping users reason over their own real data.

Useful, powerful, and sensitive - especially when money, privacy, and judgment meet.

#ChatGPT #OpenAI #AI #PersonalFinance #FinTech #Technology #InsightArea

https://t.co/bgOVjnKrhI

[Constantin Liculescu @Cl11089640]

@TheCodeMan__ AI slop

[Garry Kasparov @Kasparov63]

💔 Russia is a terrorist state, one murdering civilians with missiles with impunity as the richest nations with the most powerful military forces in the world right next door choose every day not to stop it.

[Infinite Logiz @Infinite_Logiz]

Visual Proof of (a+b)² = a² + b² + 2ab
#math #mathematics #mathskills

[Constantin Liculescu @Cl11089640]

40,000-year-old Stone Age markings may not be writing as we know it, but they could show something just as fascinating: early humans were already organizing symbols in ways that carried meaning.

A small window into human evolution, cognition, and the long road toward written language.

#HumanEvolution #Archaeology #Science #StoneAge #Writing #InsightArea

https://t.co/jn4Qi8qLVq

[Constantin Liculescu @Cl11089640]

@lexfridman so nice, have a wonderful adventure!

[DeepLearning.AI @DeepLearningAI]

Data is hungry for context.

A transcript tells you what was said. Audio can tell you how it was said. Images contain text, diagrams, and visual information. Video brings it all together over time.

Most enterprise data lives in these formats, and most of it still goes unused.

Learn how to process and retrieve across multimodal data in Building Multimodal Data Pipelines: https://t.co/CrPyZ2dcuX

[Constantin Liculescu @Cl11089640]

Building a cyberdeck is not just about making a DIY laptop. It is about turning computing into something personal again: repairable, visible, weird, useful, and shaped around how you actually think and work.

#Cyberdeck #DIYTech #RaspberryPi #Linux #ComputerScience #Programming #MakerCulture

https://t.co/UkQ3XlW82C

[Constantin Liculescu @Cl11089640]

UiPath’s new Coding Agents platform shows where enterprise AI may be heading: not just AI that writes code, but AI-generated automation that can be tested, governed, deployed, and trusted inside real companies.

The next race is infrastructure, not just demos.

#UiPath #AIAgents #ArtificialIntelligence #CodingAgents #EnterpriseAI #Automation #SoftwareEngineering #OpenAICodex #ClaudeCode #InsightArea

https://t.co/R7kRw7E5qW

[Constantin Liculescu @Cl11089640]

@DrNadolsky unfortunately they have a lot of influence...

[DeepLearning.AI @DeepLearningAI]

Slow inference. Hallucinations. Costs that don't scale.

The parts of LLMs you can't see are the parts that bite you.

Build the intuition to debug them, in our new course with @RealSharonZhou and @AMD: Transformers in Practice.

Enroll here: https://t.co/OEfy4DoLU2

[Constantin Liculescu @Cl11089640]

OpenAI’s new Deployment Company shows where AI is heading next: not just smarter models, but deeper integration into business workflows, infrastructure, and daily operations.

The hard part is no longer trying AI. It is deploying it well.

#OpenAI #AI #ArtificialIntelligence #BusinessAI #Technology #MachineLearning

https://t.co/9zQT8eAt7W

[Consensus @ConsensusNLP]

Today, we're announcing $30M in new funding to build the AI OS for Research.

2.5M researchers start their work with Consensus every month. Their work is the foundation that all progress is built upon.

We could tell you our story. We'd rather they did👇

[Constantin Liculescu @Cl11089640]

#OpenAIDevDay2026 I've built a game called Lane Strike using codex with gpt 5.5; it's already released in prod, in approaches already 1000 downloads.

Here's the link:

https://t.co/kjACWMEw1m

It's built with flutter and dart (I'm a professional programmer, but never worked with this tech stack).

The approach was spec-driven, I've touched almost no line of code. Also implemented with gpt 5.5 all: mechanic, google sign-in, interstitial and rewarded ads, analytics (developed as php backend endpoint with gpt 5.5).

Also used gpt 5.5 to interpret the analytics and improved the playability of the game (the new analysis improved the specs, and gpt 5.5 implemented the new findings).

The iterative process is so fast!

From idea to execution in almost no time (compared with the old way of doing dev, without AI and with a lot of integration problems, new language barrier etc etc).

The icon and all the grafic: all developed with gpt 5.5.