M37Labs Logo

M37Labs Feed

Knowledge base

Direct from our engineering and research Slack channels. Raw insights, technical breakdowns, field notes, and real-time updates from the M37Labs team.

M

Team M37Labs

knowledge-base
about 1 year ago

Vibe coding won’t save your career. Those who want to control the AI of the future must…

https://www.linkedin.com/posts/pawel-huryn_vibe-coding-wont-save-your-career-those-share-7372546663531495424-a8Ke?utm_source=social_share_send&utm_medium=android_app&rcm=ACoAABD5y6cB_0LtTPLOts5uEnaLNB-2vPLJ0m0&utm_campaign=copy_link
linkedin.com

Vibe coding won’t save your career. Those who want to control the AI of the future must develop tech intuition. And it's not rocket science. The best free resources to get started: - System Design… | Paweł Huryn | 31 comments

Vibe coding won’t save your career. Those who want to control the AI of the future must develop tech intuition. And it's not rocket science. The best free resources to get started: - System Design 101 by ByteByteGo (GitHub): <https://lnkd.in/dcaXetER> - Engineering Visual Guides: <https://lnkd.in/dgvvU_EZ> - Become a Supabase Pro in 1.5 Hours (1:26:39): <https://lnkd.in/dGJqThnT> - Overview of HTTP by Mozilla: <https://lnkd.in/dzSGWpyy> - HTTP Request Methods: <https://lnkd.in/d_sVPjDG> - The most important concepts of Node.js and Express.js (17:09): <https://lnkd.in/dFPvPybP> - Every React Concept Explained in 12 Minutes (11:52): <https://lnkd.in/dhXMPdQ3> - TypeScript - The Basics (12:00): <https://lnkd.in/d26iPzem> - CSP Guide by Mozilla: <https://lnkd.in/dNMhZD9v> - OWASP Top 10: <https://lnkd.in/dRPY7dGu> - CI/CD by Netlify: <https://lnkd.in/dGvrCmiX> - Overview of Test Automation with Selenium: <https://www.selenium.dev/> - Getting Started with Lovable: <https://lnkd.in/dmYVQ7fk> - Replit AI Agent, Full Course: <https://lnkd.in/drnAA6Qg> - n8n Masterclass: <https://lnkd.in/dF32BS5n> And for those building and managing AI-powered products: - Introduction to AI PM: <https://lnkd.in/dveWsD9f> - How To Build, Deploy, And Scale Your AI Product Strategy: <https://lnkd.in/dShxwfsi> - 14 Prompting Techniques: <https://lnkd.in/dnCGVH6a> - AI Evals: <https://lnkd.in/dHUFrkVs> - Error Analysis: <https://lnkd.in/d9tZcvVT> - A Guide to Context Engineering: <https://lnkd.in/d_XVN5KV> - The Ultimate Guide to AI Agents for PMs: <https://lnkd.in/dkUrHKP2> - AI Agent Architectures: <https://lnkd.in/dnmQ_kP8> - 17 Penetration & Performance Testing Prompts: <https://lnkd.in/dvZaUJ-i> - 3-Layers Distribution Framework To Win Market Share: Subscribe to get notified: <https://lnkd.in/dns_iaYG> Finally, learn by doing (no coding, understanding tech): - LLM Chatbot: <https://lnkd.in/dnUr8ivc> - RAG Chatbot: <https://lnkd.in/dew--RqD> - Voice Agent: <https://lnkd.in/dSW6_KiT> - Multi-Agent Research System: <https://lnkd.in/dpBGF3pq> - Separate DEV/TEST/PROD: <https://lnkd.in/db-xAF9z> - Full-Stack App with Lovable (2:00:00): <https://lnkd.in/dWU6yTK7> +My favorite tools in the comments. What did I forget? | 31 comments on LinkedIn

www.linkedin.com

Preview image for Vibe coding won’t save your career. Those who want to control the AI of the future must develop tech intuition. And it&amp;#39;s not rocket science. The best free resources to get started: - System Design… | Paweł Huryn | 31 comments
Link
Sep 14, 2025 • 5:25 AM
M

Team M37Labs

knowledge-base
about 1 year ago

Replit Agent 3 is out and features it brings are -

https://blog.replit.com/introducing-agent-3-our-most-autonomous-agent-yet?utm_source=alphasignal&utm_campaign=2025-09-11&asuniq=77716ee0
Replit Agent 3 is out and features it brings are -

• App Testing checks changes using a web browser to test buttons, forms, links and APIs.
• Agents & Automations enable you to build AI bots or workflow automations in plain English.
• Runs on its own for up to 200 minutes, handling tasks and recovering from errors autonomously.
Replit Blog

Replit — Introducing Agent 3: Our Most Autonomous Agent Yet

We’re excited to introduce Agent 3—our most advanced and autonomous Agent yet. Compared to Agent V2, it is a major leap forward. It is 10x more autonomous, with the ability to periodically test your app in the browser and automatically fix issues using our proprietary testing system—3x faster and 10x more cost-effective than Computer Use models. Even better, Agent 3 can now generate other agents and automations to streamline your workflows. What’s New 1. App Testing: Agent tests the apps it builds (using an actual browser) Agent 3 now tests and fixes the app it is building, constantly improving your app behind the scenes. We are launching two different options here, depending on your needs:

blog.replit.com

Preview image for Replit — Introducing Agent 3: Our Most Autonomous Agent Yet
Link
Sep 12, 2025 • 4:51 AM
M

Team M37Labs

knowledge-base
about 1 year ago

> Claude can now create and edit Excel spreadsheets, documents, PowerPoint slide decks…

> Claude can now create and edit Excel spreadsheets, documents, PowerPoint slide decks, and PDFs directly in Claude.ai and the desktop app. [...]
> File creation is now available as a preview for Max, Team, and Enterprise plan users. Pro users will get access in the coming weeks.
Then right at the very end of their post:
> This feature gives Claude internet access to create and analyze files, which may put your data at risk. Monitor chats closely when using this feature. Learn more.
And tucked away half way down their Create and edit files with Claude help article:
> With this feature, Claude can also do more advanced data analysis and data science work. Claude can create Python scripts for data analysis. Claude can create data visualizations in image files like PNG. You can also upload CSV, TSV, and other files for data analysis and visualization.
Sep 10, 2025 • 11:54 AM
M

Team M37Labs

knowledge-base
about 1 year ago

Aligning our prices and packaging with the problems we help customers solve

https://blog.cloudflare.com/aligning-our-prices-and-packaging-with-the-problems-we-help-customers-solve/
The Cloudflare Blog

Aligning our prices and packaging with the problems we help customers solve

You asked for simplicity. We listened. Introducing Externa and Interna, two new use-case-driven packages to simplify how you connect and protect your entire infrastructure.

blog.cloudflare.com

Preview image for Aligning our prices and packaging with the problems we help customers solve
Link
Aug 27, 2025 • 11:44 AM
M

Team M37Labs

knowledge-base
about 1 year ago

NVIDIA Nemotron Nano 2 and the Nemotron Pretraining Dataset v1

https://research.nvidia.com/labs/adlr/NVIDIA-Nemotron-Nano-2/?utm_source=alphasignal&utm_campaign=2025-08-21&asuniq=7cc49210
NVIDIA ADLR

NVIDIA Nemotron Nano 2 and the Nemotron Pretraining Dataset v1

NVIDA Nemotron Nano 2 is a new hybrid Mamba-Transformer reasoning model that achieves on-par or better accuracies compared to comparably sized leading open models at up to 6x higher throughput. Nemotron Pretraining Dataset v1 is a 6.6 trillion token dataset collection of web crawl, math, code, SFT, and multilingual Q&A data, used to train NVIDIA Nemotron Nano 2.

research.nvidia.com

Link
Aug 22, 2025 • 7:43 AM
M

Team M37Labs

knowledge-base
about 1 year ago

The URL context tool lets you provide additional context to the models in the form of…

https://ai.google.dev/gemini-api/docs/url-context

The URL context tool lets you provide additional context to the models in the form of URLs. By including URLs in your request, the model will access the content from those pages (as long as it’s not a URL type listed in the limitations section) to inform and enhance its response.
The URL context tool is useful for tasks like the following:
• Extract Data: Pull specific info like prices, names, or key findings from multiple URLs.
• Compare Documents: Analyze multiple reports, articles, or PDFs to identify differences and track trends.
• Synthesize & Create Content: Combine information from several source URLs to generate accurate summaries, blog posts, or reports.
• Analyze Code & Docs: Point to a GitHub repository or technical documentation to explain code, generate setup instructions, or answer questions.

Code Snippet
from google import genai
from google.genai.types import Tool, GenerateContentConfig

client = genai.Client()
model_id = "gemini-2.5-flash"

tools = [
  {"url_context": {}},
]

url1 = "<https://www.foodnetwork.com/recipes/ina-garten/perfect-roast-chicken-recipe-1940592>"
url2 = "<https://www.allrecipes.com/recipe/21151/simple-whole-roast-chicken/>"

response = client.models.generate_content(
    model=model_id,
    contents=f"Compare the ingredients and cooking times from the recipes at {url1} and {url2}",
    config=GenerateContentConfig(
        tools=tools,
    )
)

for each in response.candidates[0].content.parts:
    print(each.text)

# For verification, you can inspect the metadata to see which URLs the model retrieved
print(response.candidates[0].url_context_metadata)
Code
Aug 21, 2025 • 6:48 AM