MJH

"I expected that I was paying this fortune, all this time and energy, to learn how to think. But they are forcing you to think the way they want you to think,"

[Grok @grok]

Grok 4.5 is built for real-world engineering. It excels in large codebases and handles long-running tasks that span multiple repositories, hundreds of skills, and a variety of tools.

[𝕏erias @xerias_x]

Only one man can save US Soccer now…

[Mao Ning 毛宁 @SpoxCHN_MaoNing]

In central China’s Shanxi, a residential community has drawn attention for its “rooftop rain” — a mist cooling system that drops surface temperatures by 5–8°C in minutes.

[Miles Deutscher @milesdeutscher]

This video will make you a Claude Fable 5 expert in 20 minutes.

0:00 Intro
2:43 wtf is a loop?
5:30 Loop Engineering 101 *demo included*
8:12 Fable 5 x Claude Skills
10:10 3 ways to build effective Fable 5 Skills
12:12 Visual capabilities
14:04 Building a local memory system
18:17 How I'm personally using Fable now

[Charly Wargnier @DataChaz]

🚨 Yarchi just published an awesome guide on building an AI "second brain" using Claude and Obsidian

Based on @karpathy's LLM Wiki concept, the idea is to stop starting from a blank chat window and start building a compounding knowledge graph.

Obsidian handles the local storage.

Claude acts as the brain.

I wrote down the condensed notes on how to wire them together:

The Stack:
→ Install Obsidian (your free, local text storage) and Claude Desktop Pro (the engine that reads and writes files).

The Bridge:
→ Install the "Local REST API" plugin in Obsidian, copy the key, and use Claude’s MCP framework to connect them (claude mcp add-json obsidian-vault...).

The Context:
→ Ask Claude to interview you. Have it ask about your goals, projects, and working style, then save it all to a CLAUDE.md file so it never forgets who you are.

The Structure:
→ Create specific project folders (Inputs, Process, Outputs, Feedback) and open them as isolated vaults so Claude stays focused on one job at a time.

The Automation:
→ Save repeated workflows as markdown "skills" and use Claude's schedule tab to trigger daily vault maintenance.

Voilà!

You end up with an AI that organizes your files, summarizes your notes, and remembers your entire context.

Full guide from Yarchi here ↓

[CyrilXBT @cyrilXBT]

A CHINESE TRADER BUILT A SECOND BRAIN IN OBSIDIAN THAT GENERATES 3 TRADING IDEAS EVERY MORNING AT 6AM AND MADE $180,000 IN 6 MONTHS.

No Bloomberg terminal.
No analytics desk.
No team of analysts.

A Mac Mini by the wall.
An iPhone in his pocket.
One local Obsidian vault.

Six N8N pipelines running 24/7, pulling every article he reads, every podcast he listens to, and every voice note he drops into a Telegram bot—directly into the vault.

Every night, a neural network reads across 4,000 connected notes and finds the strongest connections between fresh information and old theses.

Every morning at 6AM, a brief lands in his inbox:

- 3 trading ideas with confidence scores
- The emerging thesis of the week
- Any note that contradicts an active position

The system only wakes him up when a fresh note contradicts his thesis, or when an idea breaks 90% confidence.

Everything else runs without him.

The monthly bill: $120 in API costs.
The monthly return: approximately $30,000 into the account.

Traditional quant funds pay teams of 8 people to produce the same flow of insights.

He pays $120 and a Mac Mini.

The full system breakdown is in the article below.

Bookmark this before you pay for a Bloomberg subscription.

Follow @cyrilXBT for every solo operator setup that changes what one person can build.

[Khairallah AL-Awady @eng_khairallah1]

Google CEO, Sundar Pichai:

"If you don't teach your agents to debug themselves now, you will keep wasting hours every week."

In 30 minutes he explains why the best engineers stopped writing code and started building agents.

Most people think building an agent requires an engineering degree.

It doesn't. It requires one guide and one afternoon.

Watch the interview, then save the exact setup below 👇

[Maxwell Orion @Orion_Vers7x]

🚨 BREAKING: Google Gemini can now analyze any stock like a Wall Street analyst (for free).

Here are 10 insane Gemini prompts that replace $4,000/month Bloomberg terminals:

(Save this 🔖 you’ll need it later)

[Ahmad @TheAhmadOsman]

Local AI hardware = capacity × bandwidth × software stack

- Capacity tells you what fits
- Bandwidth tells you how hard the box can breathe
- The software stack tells you how much of the spec sheet you can actually cash out.

Hardware by Memory Bandwidth
- Mac Studio M3 Ultra: up to 512GB @ 819 GB/s
- RTX PRO 6000 Blackwell: 96GB @ 1792 GB/s
- RTX 5090: 32GB @ 1792 GB/s
- RTX 4090: 24GB @ 1008 GB/s
- RX 7900 XTX: 24GB @ 960 GB/s
- Radeon PRO W7900: 48GB @ 864 GB/s
- AMD Radeon AI PRO R9700: 32GB @ 640 GB/s
- Intel Arc Pro B65: 32GB @ ~608 GB/s
- Tenstorrent Wormhole n300: 24GB @ 576 GB/s
- Tenstorrent Blackhole p150: 32GB @ 512 GB/s + 800G
- MacBook Pro M5 Max: 460-614 GB/s
- MacBook Pro M5 Pro: 307 GB/s
- DGX Spark: 128GB @ 273 GB/s (coherent + CUDA)
- Mac mini M4 Pro: 273 GB/s
- Ryzen AI Max / Strix Halo: ~256 GB/s (~96GB usable GPU)
- MacBook Air M5: 153 GB/s
- Snapdragon X2 Elite: 152-228 GB/s
- Intel Lunar Lake: 136 GB/s
- Snapdragon X Elite: 135 GB/s
- Mac mini M4: 120 GB/s
- Arc Pro B60: 24GB @ ~456 GB/s

Verdict

- GPUs are still the bandwidth kings

- Apple wins: stupid amounts of memory, don’t want to shard across GPUs
- Apple loses: when raw tokens/sec & concurrency matter more

- DGX Spark: coherent memory + NVIDIA stack

- Strix Halo / Ryzen AI Max: first real x86 unified-memory contender

- Tenstorrent: fully OSS stack, excited to see this mature

Fitting ≠ serving

Even if it fits, you still pay for
- bandwidth during decode
- KV cache growth
- dequantization
- batching + concurrency
- scheduler quality
- framework overhead

The only mental model that matters:

1. What must fit?
2. What bandwidth tier do I need?
3. What software stack can actually deliver it?

In short:
- NVIDIA → fastest raw speed
- Apple Studio M3 Ultra → biggest one-box memory
- Strix Halo → first real x86 unified
- DGX Spark → coherent NVIDIA dev appliance
- AMD / Intel Arc → rising alternatives
- Tenstorrent → fully opensource stack

Do ask: “which bottleneck am I buying?”

Not: “which hardware is best?”

[Soran @Soranlan]

https://t.co/KqW6SGf7nf
Anthropic工程师那句话真的绝了：

你不是该去提示Claude，你是该建一个能自己提示自己的系统。

说白了就是Loops

但大部分人搞反了

要么没记忆，每轮从头来；要么不分拆，

一个Agent扛所有

要么没刹车，睡一觉起来账单爆炸。

这三个坑，大多数踩了至少两个。

别再死磕怎么把一条prompt写得更长了，该学的是一套闭环：
有记忆、有分工、有验收标准。

没过就继续跑，过了立马停。

先看视频，然后把这套东西吃透，别等被信息淹了再翻。

不然你用的永远就是个高级聊天框。

[Rohit @heyrohitai]

Instead of watching an hour of Netflix, watch this 2 hour hour Stanford lecture will teach you more about how LLMs like ChatGPT and Claude are built than most people working at top AI companies learn in their entire careers.

[Raytar @Raytar]

Met a guy making $1.6 million a year.

Three days ago he was at a Meta conference. Told me he saw the best AI talk of his life.

Boris Cherny was on stage. Showed how the Anthropic team actually uses Claude day to day.

Boris deleted his IDE eight months ago. Now he codes from his phone.

I watched it last night. Had to pause it twice.

Not because it was hard. Because I realized I've been using Claude like a toy.

He sent me the recording. It was never published.

Posting it below.

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineers just showed how they build a full app from scratch, using a loop of agents

40 minutes from the team behind Claude Code

they used three agents: one to plan, one to build, one to judge, cycling until the app actually works

the winners won't have the smartest model, they'll have the best loop

watch it, then read the full guide on how to actually use loops below

[Ridark @ridark_eth]

I genuinely don't understand why everyone isn't using this yet

Andrej Karpathy, a co-founder of OpenAI, posted a simple idea that hit 16 million views: stop using AI to write code, use it to build a second brain.

You point Claude Code at a folder, drop in any source, an article, a transcript, a PDF, and Claude reads it, links it, and files it into a living wiki of everything you know. It compounds like interest, the more you feed it, the smarter it gets.

Here's the whole thing:

> Install Obsidian, create a vault, open it in Claude Code

> Paste Karpathy's wiki idea file and tell Claude to build it

> Claude makes three folders: raw for sources, wiki for its pages, a CLAUDE.md that runs it

> Drop any source into raw and say "ingest this"

> Ask questions across everything, forever

Five minutes to set up, and you never start from a blank chat again.

Full step-by-step guide with Claude and Obsidian, link below.

Bookmark this

[Elon Musk @elonmusk]

Your kids will love this video!

Grok Imagine prompt:
The kittens with mittens start dancing and singing “we’re kittens with mittens” with joyful, energetic movements and playful expressions.

[Elon Musk @elonmusk]

Amazing abundance for all!

[Isak @Isak_Q1]

Wait for crazy cat’s reaction 😱😱😱😱

[Isak @Isak_Q1]

I’m going to hell for laughing at this clip😱😱 The last one is dangerous😱😱

[RJ @RJDAIGOGO]

可能是我最近看过的最好的一个讲高带宽内存HBM的视频，从基本原理讲到工程工艺，顺便比较了一下内存三巨哪家强。深入浅出，推荐观看。

[Anatoli Kopadze @AnatoliKopadze]

NVIDIA CEO, Jensen Huang:

"Nobody writes prompts anymore. The new job is to write and handle loops."

This is the shift that's going to define the rest of 2026.

53 minutes of pure insight from one of the richest men on earth.

Watch it, then read the full guide on how to actually use loops below.