adrian

disrupt yourself | ex-cohere | founder

[Nick @nicks_twt]

Web app incidents timeline design

[Rahul @sairahul1]

Boris Cherny, creator of Claude Code:

"Opus 5 does in a day what used to take your team a month. Most people will keep using it wrong."

In 12 minutes he explains why Opus 5 needs less prompting than any model before, and why your old detailed prompts now work against you.

Watch it, then read the article below on how to prompt Opus 5 👇

[codila @0xCodila]

Google just released free 1-hour course on building agentic knowledge Graphs from 0% to 100%:

10% → 4:01 - how to build a GraphRAG agent
30% → 15:00 - Graph Engineering explanation
55% → 30:00 - Agentic search Engineering
80% → 35:48 - Graph Engineering practice
100% → 47:06 - self-improving agents in graphs

this free Google course mass replaces a $500 graph engineering bootcamp - learn it in 60 min to 100%

watch it today - then read the full graph playbook in the article below ↓

[Anatoli Kopadze @AnatoliKopadze]

A Google Cloud engineer just showed how to build a full app with Claude from scratch.

He spent 26 minutes live on stage doing what most teams take weeks to do.

Worth more than any $500 vibe-coding course, no team, no setup, just Claude and a goal.

The ones who learn what Claude actually does are shipping what everyone else outsources to a team.

Watch it, then read the guide below on the Claude features 99% of users never find.

[Harrison Chase @hwchase17]

So i didn’t really know what graph engineering is, and i still don’t really… but it’s basically just langgraph?

[Ruben @rdominguezibar]

Kimi's CEO🇨🇳 says every AI lab has the wrong obsession

Zhilin Yang, on why K3 beat the frontier: "Every lab, like Claude, thinks the model matters most. That's wrong. It's how you organize the people building it that wins."

Then Moonshot proved the philosophy. K3 sold out every plan on purpose, cutting their own revenue instead of throttling existing users. When Anthropic hit that wall in April, they cut users' usage 50% at peak.

His one big idea: long context is the AI era's RAM. The 128K-to-gigabytes jump, compressed into 2 years instead of 40.

The real moat: "your biggest advantage, perhaps your only advantage, is your organization."

Model, or the team behind it: which actually wins?

[st1ne @SolSt1ne]

A former chess prodigy co-founded Palantir at 22, cashed almost nothing for years, and turned that into an empire - 8VC, Addepar, Anduril, a whole university.

- Peter Thiel's protege who became a company-building machine

56-min unfiltered on defense tech, AI, and where the next $100B companies come from

bookmark - this rewires how you think about building anything

[Don Quijote de la IA @IA_Quijote]

🚨 Guarda esta clase magistral de 1 hora.

Se llama “How to Speak” y durante más de 40 años fue una de las charlas más legendarias del MIT.

Patrick Henry Winston, profesor del MIT, tenía una idea muy simple, tu forma de comunicar puede cambiar tu vida.

[Ben @bensenescu]

Introducing OpenSEO, the open source alternative to Semrush and Ahrefs.

I started building it out of spite because the existing tools were too expensive, bloated or scammy.

Since then, we've gotten 4k stars on Github and are launching on Product Hunt today.

Hope you support!

[Codez @0xCodez]

Andrew Ng just released a 1-hour course on building agentic knowledge Graphs from scratch:

• 00:00 - Introduction to agentic knowledge Graphs
• 03:07 - Construction of agentic Graphs
• 14:00 - Architecture of multi-agent systems
• 23:00 - Building agentic graphs with Google ADK
• 01:06:03 - Why Graphsare the future of agentic AI

Worth more than 10 articles on loop engineering.

Watch it today, then read how to become a graph engineer in the article below.

[rari @0xwhrrari]

4 Anthropic engineers just shared one hour of their best prompting lessons

One of the most valuable prompting masterclasses on the internet and it's completely free

14:12 - Real prompts used inside Anthropic
32:33 - The simple fix that improves your prompts
59:44 - How to give Claude the context it actually needs
1:07:59 - The prompt that keeps working while you sleep

Spend one hour learning from the people who write prompts at Anthropic

Worth more than most paid vibe coding courses

Bookmark and watch it tonight

Then read the step-by-step guide below

[Alok Kumar @Alokkumarzz]

In 2008, Malcolm Gladwell explained why some people succeed and some don't in a single 1-hour talk.

This will permanently change the way you think about talent, effort, and success.

Bookmark & watch today, no matter what.

[Akira @awp_Akira]

THIS YOUNG GUY MADE $28,400 BUILDING 3D WEBSITES FROM ONE PROMPT

he turns a single line of text into a full scroll based website with real depth and motion baked in

you describe the site you want and the AI writes the whole front end, the 3D scene and the scroll interactions in one pass

it wires up the camera moves so the page reacts as you scroll, parallax layers, objects that rotate, sections that build in

what used to take a WebGL developer 2 weeks now lands in an afternoon

studios charge 5k to 15k for one immersive site like this and clients cannot tell a person did not hand code it

this is a small slice of how I run everything solo, one operator and a stack of AI doing the heavy build

start now while most agencies still think this needs a 3 person team

[Mathias @MathiasChu]

Hoy Meta comunicó oficialmente que su MCP ya está disponible para cualquiera que quiera desarrollar.

La idea es que puedas hablarle con lenguaje natural a la plataforma y puedas:
- crear/editar campañas, ad sets y ads
- hacer reporting detallado
- gestionar catálogos y feeds
- correr A/B tests
- revisar logs de actividad

El valor deja de estar en hacer clicks en la plataforma y pasa a entender qué preguntas tiene sentido hacerse.

[LangChain @LangChain]

We've built a full software engineering agent factory in house, and open-sourced every piece of it. @BraceSproul's blog dives into each of those components, what they're used for, and why them being OSS matters

[Vaibhav Sisinty @VaibhavSisinty]

Moonshot AI CEO Yang Zhilin just broke down exactly how they built Kimi K3.

And it's the clearest explanation of frontier AI training I've ever seen.

[me @twetsfyp]

This person gave Claude Code the ability to copy the design of any web.

Created an MCP that reads the HTML/CSS of any site and extracts colors, typography and components.

Result: Clean UIs at last.

Save it🔖

[Roan @RohOnChain]

My friend applied to 300 tech jobs in two years. No MIT. No Stanford.

Last month Anthropic offered him $750,000.

I asked him how he broke in from zero.

He sent me the exact video that got him in. Andrej Karpathy's 3-hour course on building a full LLM from scratch.

Anthropic's own researcher shows you how LLMs like ChatGPT & Claude are actually built.

I watched it last night.

Halfway through, I realized it's embarrassingly simple to break into an AI lab.

Bookmark this and read the article below.

• 00:00 - intro to LLMs
• 12:41 - LLM training pipeline
• 31:58 - LLM tools & plugins
• 41:14 - LLM transformer architecture
• 2:19:02 - scaling the LLM

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineer:

"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

In 45 minutes she breaks down how Anthropic builds agents that remember, learn from their mistakes, and get smarter with every run.

Worth more than any paid course you'll find on building agents.

Watch the session, then read the guide on building loops below.

[Maxim Kuznetsov @disarto_max]

Opt-in-performance (dark mode)