@dr.nerd

Machine Learning, Data Scientist &
Web developer

[Claude @claudeai]

Claude Code on desktop can now preview your running apps, review your code, and handle CI failures and PRs in the background.

Here’s what's new:

[Claude @claudeai]

Introducing Claude Code Security, now in limited research preview.

It scans codebases for vulnerabilities and suggests targeted software patches for human review, allowing teams to find and fix issues that traditional tools often miss.

Learn more: https://t.co/n4SZ9EIklG

[@dr.nerd @DataNerdke]

@akinyi__wendy You DM is locked

[F.O.L.A @folaoftech]

Difference between Machine learning vs Deep learning 💨🫡

[Virus Bulletin @virusbtn]

Infoblox Threat Intelligence uncovers Evilginx-based SSO phishing using subdomains that mimic university portals, targeting at least 18 US institutions since April 2025, and finds nearly 70 related domains for future tracking. https://t.co/9ZZTg2RhuR

[@dr.nerd @DataNerdke]

@mbiti_mwondi Try https://t.co/56eRUmaa2J save yourself from a lot

[@dr.nerd @DataNerdke]

We’re a week out from #AgentsInProduction 2025!
I’ll be speaking on the AI Workforce track about
“Deploying AI Agents for Scalable Immigration Automation.”
Register: https://t.co/Vu2VHvuIrY
@mlopscommunity @prosus @demetriosbrinkmann
#AI #MLOps #Automation #AIWorkforce

[@dr.nerd @DataNerdke]

Check out my latest article: The Evolution and Battle of Open vs. Closed AI Models: Beyond Imagination and Into Reality https://t.co/vbANLPa2KG

[LangChain @LangChain]

💡David Tag from @LinkedIn reveals how they built their first production AI agent for hiring using LangChain and LangGraph. Learn the technical architecture behind LinkedIn Hiring Assistant and the framework that scaled AI development across 20+ teams.

Watch the full session here: https://t.co/OHU7hZGIQf

Catch up on all the talks from Interrupt: https://t.co/DKFcrR2KsQ

[Akshay 🚀 @akshay_pachaar]

Let's build an MCP server that connects to 200+ data sources (100% local):

[Santiago @svpino]

A complete roadmap to learn how to build AI Agents:

1. Build a strong foundation in Python
2. Learn how to work with RESTful APIs
3. Understand how Large Language Models work
4. Get familiar with the OpenAI API
5. Understand how vector databases work
6. Learn how to create and retrieve embeddings
7. Learn about caching and persistent memory using databases
8. Learn to build APIs with Flask or FastAPI
9. Master prompt engineering techniques
10. Study how to build RAG applications
11. Explore agentic frameworks (LangChain, LangGraph)
12. Learn how to connect agents with external tools (MCP)
13. Learn how to containerize and deploy agents with Docker
14. Understand how to limit agent behavior
15. Learn how to implement safety guardrails

For those of you who are looking to learn how to build agents, check out the "AI Agents with LangChain and LangGraph" course on Udacity.

(I pasted the link in a reply to this post so I don't get throttled.)

This is a course that focuses on the core ideas of building agents. The final lesson of the class is a project where you'll build a complete agent.

This course will take you one weekend of work, and will teach you what's probably the hottest skill in the market right now.

[@dr.nerd @DataNerdke]

@globalreena @morphnetwork Great 😃

[@dr.nerd @DataNerdke]

@ywli_info I’m part of a student team from Masinde Muliro University building HerVoice—a platform to fight femicide & GBV in Kenya through AI-powered awareness and secure reporting.

We’re looking to connect with NGOs or global partners to help scale it. If you know anyone, a plug kindly

[@dr.nerd @DataNerdke]

@covaw @AfyAfrika @EwanganEwangan @TheGirlGen @CSONetwork @voicetweetz @amplifyfund @UNFPAKen @OptionsinHealth I’m part of a student team from Masinde Muliro University building HerVoice—a platform to fight femicide & GBV in Kenya through AI-powered awareness and secure reporting.

We’re looking to connect with NGOs or global partners to help scale it. If you know anyone, a plug kindly

[@dr.nerd @DataNerdke]

@GBVnet I’m part of a student team from Masinde Muliro University building HerVoice—a platform to fight femicide & GBV in Kenya through AI-powered awareness and secure reporting.
We’re looking to connect with NGOs or global partners to help scale it. If you know anyone, a plug...

[@dr.nerd @DataNerdke]

And that’s okay—some faces were just born to be visually interesting.We respect the art, but we also respect the real. Si kila sura ni ya animation, na si kila animation inafaa kila sura. But hey, it’s the effort that counts, right?

[@dr.nerd @DataNerdke]

Since Studio Ghibli ilitokea kwa mlipuko wa AI art, kila mtu sasa anataka kuwa cartoon. Ukiangalia timeline ni kama umeingia anime convention ya Nairobi—watu wamegeuka characters straight outta a Miyazaki fever dream.

[@dr.nerd @DataNerdke]

But let’s be real… some folks still maintain their unique facial features—ile charm ya uso wa kawaida, raw and untouched by filters. The AI tried its best, lakini kuna sura hazigeuki Totoro no matter how much you upscale.