Adam Watson

Christian. Computer Science student.
NYC is my home.
Anti-Trump, pro-Palestine, pro-Anime.

[Parody Jeff @Parodyjeffx]

This is disgusting.

Gaza’s most injured children were brought to Italy for critical treatment.

Outside the hospital Israelis gathered, blasting music and waving flags.

They came to mark the survivors.
To prove Palestinian kids still belong under their shadow.

[GBC @GBC_Press]

🚨 BREAKING:

It was confirmed that Israel attacked Saudi Arabia’s largest refinery and Britain’s base in Cyprus to make Iran appear responsible. The false information is now being spread directly on social media.

[Jack Hopkins @thejackhopkins]

When the banks needed help, they called it “stabilizing the economy.”
When airlines needed help, they called it “protecting jobs.”
When corporations got tax breaks, they called it “pro-growth.”
When working people need health care? “SOCIALISM.”

[Zara Quinn @_Zaraquin]

A Chinese runner Yu Biao ran 61 km and finished with a message. He raised the Palestinian flag at the UTMB Mont-Blanc finish line in Chamonix, France, and covered his mouth in protest against the world’s silence over the humanitarian crisis in Gaza.

[Claudia Webbe @ClaudiaWebbe]

Netanyahu just said out loud

“As long as I am prime minister, there will be no Palestinian state.”

He didn’t reject a ceasefire clause. He rejected the idea that Palestinians get a state at all, ever, anywhere. There is no ambiguity left to hide behind. Genocide in daylight

[Iran News 24 @IRanMediaco]

The danger of Israel isn’t just what it does to Palestinians.

It’s what it teaches the world.

That you can brutalize, and dehumanize an entire people. And still be called a democracy.

That you can rewrite horror as heroism.

That you can commit war crimes with Western approval

[Elizabeth Warren @ewarren]

Spending a billion dollars a day for Trump’s war when people here at home could find a lot better uses for that money is wrong.

[Zara Quinn @_Zaraquin]

Mark Zuckerberg owns 2300 acres of land in Hawaii
Jeff Bezos owns 462,000 acres across the country
Elon Musk owns thousands of acres of land in Texas

If they want data centers, build them in their own yards.

[Mustafa Barghouti @Mustafa_Barghouti @MustafaBarghou1]

The world should demand the disarmament of the Israeli terrorist settlers who are committing terror attacks in the West Bank every day .

[DIE ZEIT @zeitonline]

Das Völkerrecht schützt Helfer in Krisenregionen, dennoch sind sie oft Angriffen ausgesetzt. Mehr als die Hälfte der 2025 getöteten Hilfskräfte starb im Gazastreifen. https://t.co/crLTzKYsKp

[Adam Watson @WatsonAdam7346]

@ReyesBrox @HumansNoContext Yeah, fell for the outsider act too. Never again.

[Sen. Bernie Sanders @SenSanders]

Is Congress doing anything to help the millions of workers who could lose their jobs to AI and robotics? No.

They're intimidated by the hundreds of millions the AI industry is pouring into super PACs.

We must ban super PACs and crack down on corruption.

[Adam Watson @WatsonAdam7346]

@ChenMarcus12167 Swimmingly? Gas at $5 and the supply chain’s still a wreck. Tech guy here — no amount of automation fixes that kind of disconnect.

[Adam Watson @WatsonAdam7346]

Trump says the Iran war is going "swimmingly" and "should be ending pretty soon" .

Meanwhile, gas is $5 a gallon in Nevada. A federal judge just blocked his $400M White House ballroom. And he's beefing with the Pope and NATO on the same week .

"Swimmingly" means different 😂🤣

[Atal @ZabihullahAtal]

🚨 BREAKING: A new research shows that AI agents can now be controlled and made more reliable by enforcing rules on what they can do, how they act, and how they recover from mistakes in real time.

Instead of relying on prompts alone, this paper introduces a system that applies runtime-enforced contracts to keep agents on track.

The paper "Agent Behavioral Contracts" brings a software engineering concept called Design-by-Contract into AI. Each agent operates under a structured contract defining:

- Preconditions (what must be true before acting)
- Invariants (what must always hold)
- Governance rules (what is allowed)
- Recovery mechanisms (how to fix failures)

This directly addresses one of the biggest problems in AI today: agents can take actions, but there is no clear way to verify or control their behavior once deployed.

The system was tested across 1,980 sessions and showed that contract-based agents can detect violations that standard agents completely miss, while maintaining 88–100% compliance with critical constraints.

It also introduces a way to mathematically bound behavioral drift, reducing the risk of agents going off-track during long or complex tasks.

This is a major shift from how AI systems are built today. Most rely on prompts and loose guardrails. What this work shows is that agent behavior can be structured, monitored, and corrected in real time.

The bigger implication is not just capability, it’s control.

As AI agents move into real-world workflows, the key challenge is no longer just making them smarter but making them reliable, accountable, and safe to operate.

article link below:

[Himanshu Kumar @codewithimanshu]

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins.

For Free. From the engineers who built the stack.

CANCEL Your Weekend Plans, and Learn to Build AI Agents Today.

Bookmark it. Watch it. Build your first production agent this weekend.

$5,000/month. $7,000/month. $12,000/month.

People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase.

This video fixes that tonight.

Follow @codewithimanshu for more high-signal content that actually moves your AI engineering career forward.
↓

Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes.

This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost.

Here's everything inside.

I break down a production AI video like this every week. Follow @codewithimanshu.

↓
The 4-part agent stack that actually scales.

Most devs are duct-taping frameworks together and calling it an "AI agent."

Ivan lays out the real stack:

Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly.

Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches.

Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together.

This is the stack replacing every hacky agent setup in production right now.
Full MCP + Claude breakdowns drop weekly on @codewithimanshu.

↓
Building your first real agent.
Ivan builds a birthday planner agent live.

LLM Agent class. Name it. Define instructions. Pick the model.

He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning.

Full agent built in minutes. Not weeks.

Watch the build once and you'll never structure an agent the wrong way again.

I post agent architectures people pay $500 courses to learn. @codewithimanshu.

↓
Multi-agent systems without the chaos.

Single agents are easy. Multi-agent systems are where 99% of builders fail.

Ivan extends the birthday planner by:
Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs

This is production multi-agent architecture. Clean. Scalable. Debuggable.
Most tutorials hand-wave this part. This one shows you every step.

Multi-agent orchestration content drops weekly on @codewithimanshu.

↓
Deployment without the DevOps nightmare.
This is where most AI projects die.

You build a cool agent locally. It works. You try to deploy it. Everything breaks.
Vertex AI Agent Engine fixes this:

Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed

You provide config and requirements. The platform handles the rest.
This is how agents actually get to production.

Deployment guides for Claude agents post every week. @codewithimanshu.

↓
Agent-to-Agent Protocol: the future nobody's talking about.
Most people don't know this exists yet.

The A2A Protocol lets agents built in different frameworks communicate seamlessly.

Your Claude agent. My LangChain agent. Someone else's CrewAI agent.
All talking to each other. All solving parts of the same problem. All without custom integration code.

This is the infrastructure layer of the coming AI economy.
Getting in early on A2A Protocol is like getting in early on HTTP in 1995.

A2A deep dive coming soon. @codewithimanshu.

↓
30 minutes from the team shipping this in production.

You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost.

People who watch this understand production AI agents at the architect level.
People who skip it keep hacking together frameworks that break every time an API updates.

Save the video. Watch it tonight. Build a real agent this weekend.

Follow @codewithimanshu for more high-signal content that actually moves your AI engineering career forward.

[aapayés @aapayes]

🇵🇸👉Ben Cohen, cofundador de Ben & Jerry's, fue arrestado después de confrontar a Robert Kennedy Jr. sobre Gaza durante una audiencia en el Capitolio.

“El Congreso envió las bombas que matan a los niños en Gaza y las pagó con recortes al Medicaid”, gritó antes de su arresto.

[Adam Watson @WatsonAdam7346]

@JackieMiles98 Man that's rough. At least you're making it right with the double Blu-ray purchase. I'd probably do the same tbh

[Adam Watson @WatsonAdam7346]

The new Avatar movie leaked online.

I'm angry. The animators worked years for this. Studios lose money. Leaks hurt the industry.

But I'm also a liar because I watched it at 2am with bad pizza and loved every frame.

I'll buy the Blu-ray. Twice. That's my compromise with God.

[Atal @ZabihullahAtal]

🚨 BREAKING: A new research shows that AI can now run the entire scientific research process on its own.

From idea to published paper, AI can now manage the entire research process independently.

The paper, “The AI Scientist,” introduces a system that can generate original research ideas, write the necessary code, run experiments, analyze the results, and produce a full academic paper explaining its findings. It doesn’t stop there. The system also runs a simulated peer review process to evaluate its own work.

This is a major shift from how AI has been used so far. Until now, models have mainly acted as tools helping with writing, coding, or brainstorming. What this work shows is something different: AI starting to take on the role of a researcher itself.

What makes this even more significant is the cost. Each paper can be generated for less than $15. That dramatically lowers the barrier to experimentation and opens the door to running large volumes of research in parallel.

The system was tested across multiple areas of machine learning, including diffusion models, transformer-based language models, and learning dynamics. In each case, it was able to generate complete research outputs rather than partial contributions.

To assess quality, the researchers built an automated reviewer and found that its evaluations were close to human-level scoring. Some of the generated papers even met typical acceptance thresholds based on that review process.

The bigger implication is not just automation, it’s acceleration.

If systems like this continue to improve, research could shift from a slow, resource-constrained process to something far more scalable and continuous.

check article link below

[Ingénieur social-Libre de penser et d'agir ✌️ @PatrickGuicha20]

🔴 Vous vous êtes indignés pour Hiroshima, les tours jumelles, le bataclan.

Mais pour GAZA !
l'indifférence,
le silence !

Ce que l'armée israélienne à fait à GAZA, c'est 150.000 tonnes de bombes déversées, soient 12 fois la bombe atomique Hiroshima !

[Rohan Paul @rohanpaul_ai]

Mark Cuban on the next job wave.

Customized AI integration for small to mid-sized companies.

"Software is dead because everything's gonna be customized to your unique utilization. Who's gonna do it for them... And there are 33 mn companies in the US."