How to become expert at thing: 1 iteratively take on concrete projects and accomplish them depth wise, learning “on demand” (ie don’t learn bottom up breadth wise) 2 teach/summarize everything you learn in your own words 3 only compare yourself to younger you, never to others

x.com/i/article/1909…

UC Berkeley open-sourced a 14B model that rivals OpenAI o3-mini and o1 on coding! They applied RL to Deepseek-R1-Distilled-Qwen-14B on 24K coding problems. It only costs 32 H100 for 2.5 weeks (~$26,880)! It's truly open-source. They released everything: the model, training

From a dev at a large tech company: “We were only allowed to use GitHub Copilot as an AI IDE. It was OK. But then more and more of us used Cursor on side projects and it was *so much better* Luckily we have have a dev platform team and we told them we want to use Cursor. So

I added a Knowledge Graph to Cursor using MCP. You gotta see this working! Knowledge graphs are a game-changer for AI Agents, and this is one example of how you can take advantage of them. How this works: 1. Cursor connects to Graphiti's MCP Server. Graphiti is a very popular

we wrote a guide on how to work with documentation in Cursor includes some guidance on when to use which tool, a quick MCP server example for internal docs, and some prompting tips

"after 6 months of daily AI pair programming, here's what actually works"

Andrej Karpathy literally shows how to build apps by prompting in 30 mins

Context Engineering Guide I'm writing a detailed guide on context engineering for AI devs. v1 is out now! (bookmark it) I use a concrete deep research multi-agent example to show what context engineering involves.

Deep dive into Playwright theory and use cases awesome-testing.com/2025/07/playwr…

Santiago This slide from an Anthropic talk is the most clear explanation I’ve seen so far: agents have cycles in their prompts and tool calls, workflows are like dags

💡 New blog post: AI Tooling for Developers Landscape 2025 From project bootstrappers and CLI tools to autonomous agents and AI-powered IDEs. awesome-testing.com/2025/07/ai-too…

The Agentic Web is upon us! If you want to learn about the Agentic Web, look no further. This new report is a banger! It presents a detailed framework to understand and build the agentic web. Here is everything you need to know:

jeff Any model, but you need to say "my friend has this idea and I'm trying to talk him out of it"

Afera z KPO wyszła na jaw tylko dzięki jawności danych. Wyobraźcie sobie, że mamy takie same mapki pokazujące, na co wydaje się publiczne pieniądze w każdej gminie i powiecie. Może wtedy udałoby się stanąć do realnej walki z korupcją w samorządach?

Podsumowanie KPO HoReCa: - suma wsparcia: 1.192.052.858 PLN (ponad 1mld) - średnia kwota: 412.617 PLN - ilość firm: 2889 - ilość wystąpień słowa "dywersyfikacja": 1621 Z uwagi na niedostępność strony, kopia danych u nas: kamienikupa.com/files/kpo-hore… (jak chcecie surowy CSV,

very, very, very few people understand how to be productive, and really, how productive you can be, with LLMs for coding what i didn't expect is how few people would actually pick up on it. Like, the saturation point is an extremely small number of people

Niestety, ale będą złe informacje z Ukrainy. W ciągu ostatnich 72 godzin na front między Kramatorskiem a Pokrowskiem doszło do katastrofy po stronie ukraińskiej. Z lokalnych źródeł wiem, że sytuacja na północ od Pokrowska jest gorsza niż podaje Deep State. Potwierdza to wiele

The URL context tool is now generally available in the Gemini API and comes packed with new features! The tool lets you provide additional context to the models in the form of URLs and now also has image and PDF endpoint support! Makes adding context for Gemini much easier :)

Anthropic continues to crush it with these guides. This is a good example of what context engineering involves.