Polar Lights

Kirill Pavlyashik, also known as Kirill Polar Lights, works at the intersection of ambient, glitch and techno.

[Polar Lights @Kirillirikk]

https://t.co/J6gLrA0MG6

[Demis Hassabis @demishassabis]

https://t.co/PTeDiv1b6L

[Eswar prasaath @Eswarprasaath_]

A Professional Creative tool that creates any simulation or 3D model in minutes with just a single prompt . With lot of controls and features to actually create a beautiful visuals and simulations that is production grade to be used on anywhere.

I have created this beautiful abstract 3D model by giving this prompt with a reference image within 5 minutes.

Will be Shipping this tool on next month, date will be announced soon.

Prompt: Let's create a beautiful and accurate simulation of the attached image

Reference image: Result:

[Eswar prasaath @Eswarprasaath_]

If you can type a sentence like this
" Let's create a Enzyme kinetics: substrate molecules binding and releasing from active site swarm "

Within 5 minutes, you see this simulation.
Isn't it feel magical?

Every time I test this tool, it impresses me with a beautiful simulations like this.

I am excited to see what people are going to create with this creative playground.

Stay tuned for the launch update.

[kai @0xkkai]

SOMEONE FROM THE ANTHROPIC TEAM LEAKED THEIR OBSIDIAN SETUP. 8 MILLION PEOPLE SAW HOW HE ACTUALLY USES CLAUDE

the funniest part? all of this information was sitting in claude's documentation from day one. nobody read it

one guy did, packed it into a 9-step guide and posted it. and it broke the internet. 4,100 likes, 800 retweets, then china picked it up and 8 million views

want to know what's in it?

one file. called CLAUDE.md. it holds everything about you: how you think, what you're working on, where you get stuck, even how you want the ai to talk to you. claude reads it first every single session

one file changed everything. because now ai doesn't open with "how can i help?" it already knows. it remembers your projects, sees your goals, catches moments where you're contradicting yourself

people spent years searching for the perfect prompt. the right temperature. the magic formula. and the answer turned out to be not how you ask ai. but what ai knows about you before you even open your mouth

then the guy went deeper. taught claude to work on a schedule. every morning at 7am the ai walks through all notes on its own, finds new stuff, links it, cleans what's stale. no command. no reminder

and all of this runs on obsidian. free app. text files on your drive. no cloud, no lock-in. switch models tomorrow and the folder keeps working

the most liked comment under the original post: "this is the difference between using ai and building a system. most people won't realize it until they waste hundreds of hours repeating themselves"

hundreds of hours. you've already spent some of them

full guide in the video. i break down finds like this every day - follow so you don't miss the next one

[0xMarioNawfal @RoundtableSpace]

**ANDREJ KARPATHY JUST PACKED 8 YEARS OF OPENAI AND TESLA EXPERIENCE INTO ONE FREE 2-HOUR LECTURE.**

[AdiiX @adiix_official]

THIS DEVELOPER JUST KILLED THE ENTIRE VOICE CLONING INDUSTRY WITH ONE GITHUB REPO

Claude now speaks in your own voice across 23 languages through a single MCP call.

Free. Local. Offline.

ElevenLabs charged $22-$330 a month for what Jamie Pine just gave away under an MIT license.

Claude Code, Cursor, and Cline hook in with one command and start replying in your cloned voice straight from the terminal.

→ developer Jamie Pine dropped the repo jamiepine/voicebox on GitHub 41.6k stars in a matter of weeks

→ clones any voice from 10 seconds of audio, seven TTS engines to choose from

→ runs on your own machine via Tauri (Rust, not Electron) voice and samples never leave your computer

→ Claude Code, Cursor, Cline, and any MCP-aware agent speak back in your chosen clone through a single voicebox.speak call

→ plus global dictation with one hotkey inside any app

→ generate content in Arabic, Japanese, or Polish without opening your mouth

Replaces ElevenLabs and WisprFlow in one MIT-licensed app.

Bookmark this for the moment you want to give your agent a voice, repo below 👇🏻

[Matthew Berman @MatthewBerman]

Is it appropriate to ask another man about his J-space?

[ₕₐₘₚₜₒₙ @hamptonism]

Peter Thiel literally walks you step by step on how to succeed in 2026:

[Travis Fischer @transitive_bs]

just released a lil tool to convert notion docs to markdown for LLMs

npx -y notion-x-to-md 067dd719a912471ea9a3ac10710e7fdf

✅ supports all public notion blocks including collections
✅ renders embedded tweets
✅ free; no API key needed
✅ open source https://t.co/gYPgwVQq9B

[reuben @reubbr]

You write the invariant once as a small formal spec. A generator projects it into your real language as guard types the compiler won't let the model violate.

The agent writes ordinary Go (or TS, or whatever). It simply can't construct the unsafe value.

Full write-up + runnable demo:
https://t.co/lXLWvOzL0k

[Rohit @heyrohitai]

🚨 Anthropic just showed a 27-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch it and bookmark it now.

[Viktor Oddy @viktoroddy]

❤️‍🔥Gemini 3.5 Flash is so cracked at animated websites.

Just Recorded a 25 min Tutorial on how to Design websites with Google AI Studio + Gemini 3.5 ($50k Website)

[Curious Refuge @CuriousRefuge]

We tested @HappyHorseATH 1.0 against @Seedance__ai 2.0 across water physics, fire physics, VFX, everyday interaction and conversations shots, and the results were kind of surprising. Seedance still comes out ahead overall in our opinion.

While Happy Horse was able to follow most of the prompts and generate the intended actions, its outputs especially in larger action-heavy shots tended to drift away from the original reference image and start to resemble video game cinematics rather than live-action footage. Seedance, on the other hand, preserved realism and image fidelity better overall.

That said, it’s still pretty impressive how quickly Happy Horse came out of nowhere and got this close to some of the leading video models already.

[Blaze @browomo]

This Chinese guy created agents in Claude Code for landing pages and single-handedly serves 47 small businesses a month, taking $400 from each.

He built a system of 7 agents on Claude Sonnet 4.6 that analyzes Google Maps in small towns, finds small businesses without websites there, and over 1 weekend takes each one to a finished mockup with video and cold message.

No assistant, no sales team, no SDR. Just him, a MacBook, an iPhone, and 1 API key.

And traditional web design agencies keep teams of 8 people on salary for the same order flow, while his expenses are only tokens and subscriptions to Lovable, Higgsfield, and Calendly.

7 agents work through 1 orchestrator on Claude Code Router. Usage is about 3 million tokens a day, the average API bill is about $480 a month.

All 7 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions, and 1 of them lives right in the iPhone and picks up positive replies from the subway, a taxi, or on walks.

And here is the system prompt he put into the orchestrator before launch:

"You are the orchestrator of a solo agency that sells ready-made websites to local businesses. You delegate read-only tasks to 6 sub-agents and own all writes.

sub-agents:

// Scout (walks through Google Maps in selected cities, looks for narrow niches: 5+ years on the map, fewer than 50 reviews, no website or a website from 2014, but high ratings)
// Diagnoser (for each lead writes a 50-word diagnosis, hero angle, tone matched to the industry, and a cold message under 70 words)
// Builder (generates a landing page mockup in Lovable through MCP only for the top 5 leads per day, with the sharpest diagnoses and the biggest gap)
// Filmer (pulls 5 screenshots of the mockup and through Higgsfield renders a 10-second vertical video 1080x1920 with a soft zoom)
// Pitcher (sends a personalized cold message through the right channel for the niche: email to roofers, SMS to tradesmen, IG DM to salons, LinkedIn to realtors)
// Checker (runs every message through evals for personalization, absence of AI markers and buzzwords before sending)
// Mobile (lives in the iPhone, handles positive replies in real time, books Zoom calls in Calendly through MCP while the owner is on the go).

You never let 2 sub-agents touch 1 lead. You stop and request approval from the human only when a deal exceeds $3,000 or the reply rate in a niche for the day drops below 12%."

Meaning the system knows what it is and within what boundaries it is allowed to act.

It knows it is supposed to find leads on its own.

It knows it is supposed to take each one to a mockup, video, and cold message without intervention.

It knows the human only steps in when a deal goes above $3,000 or the reply rate stops converging.

→ The system runs 24 hours a day

→ Scout goes through about 220 local businesses on Google Maps per day and leaves 30 new leads in the queue

→ Diagnoser outputs 30 structured diagnoses + briefs + cold messages per day

→ Builder assembles 3 to 5 finished landing pages in Lovable for the sharpest leads

→ Filmer renders a 10-second vertical video in Higgsfield for each one

→ Pitcher sends 30 personalized messages per day across 4 channels with a reply rate of about 14%

→ Checker runs every message through evals before sending

And only when a deal breaks $3,000 or the reply rate for the day drops below 12% does the orchestrator wake the owner.

And when the owner at that moment is sitting in the subway or a taxi, the Mobile agent in his iPhone picks up 1 move on its own: replies to a fresh positive reply from a dentist, books a Zoom through Calendly synced to the local time of the client, and puts the lead back in the queue. The owner only has to tap "approve" and in just 10 minutes join the call.

Here is what the system writes in his log during 1 of the Saturdays:

"scout report: 218 businesses checked in Austin, Denver, and Miami, 34 without a website, 19 with a website from 2014, 6 with an active redesign request in reviews. passing top 30 to diagnoser."

"pitcher: 30 cold messages sent across 4 channels, 14 replies, 5 positive, 3 Zoom calls booked for Sunday. passing to closer."

"builder: landing page for Westside Cosmetic Dentistry built in Lovable, 5 sections, mobile, soft beige. URL placed at /Users/dev/maps-agency/clients/westside/v1. filmer launching Higgsfield."

"eval flag: deal with The Lotus Salon at $3,400 exceeds the approved limit of $3,000. sending for manual review."

He has no server of his own and no separate backend.

Just a local file sandbox at /Users/dev/maps-agency, an MCP router, 1 API key to Claude, and the same key forwarded to Claude Code on his iPhone.

Out of everything I have seen this year, this is the cleanest one-person agency for selling websites to small businesses: $480 a month on the API, about $18,800 into the account, and between them 7 prompts, 1 file system, and 1 phone in the pocket.

[ₕₐₘₚₜₒₙ @hamptonism]

The Big Book of Large Language Models:

[divyansh tiwari @DivyanshT91162]

In 2019, MIT neuroscientist Nancy Kanwisher gave a 1-hour talk on how your brain shapes your mind.

Be sure to watch and save it—it will change the way you think.

[Meta Alchemist @meta_alchemist]

designing with Codex is goated now with image gen 2 + vision combo.

this dude literally created a full game inside Codex.

you can learn how to master designing any sort of user interface and experience with the guide below, too:

[Indu Tripathi @InduTripat82427]

The person who built Claude Code just showed exactly how to use it.

30 minutes. Free. Straight from Boris Cherny himself.

Bookmark this before you forget.

Most people using Claude daily are missing 40+ features hiding in plain sight.

This single session is worth more than any $1000 course.

[Andrew Carr 🤸 @andrew_n_carr]

somebody made a huggingface model visualizer!! just plug in the url and explore at any granularity

[雨哥向前冲 @xiangxiang103]

AI 虚拟女友一个月赚4.3万美金！

我今天看到这个帖子，直接看呆了。

一个21岁的 Austin 大学生，用 AI 造了一个叫 Maya 的 OnlyFans 账号，第一个月就赚了4.3万美元。 问题是——照片里那个女孩，根本不存在。

Maya 22岁，UCF 心理学辍学生，1247个付费订阅者，单月最高一个粉丝就刷了1847美元。

她没有拍视频，没有真人打字，所有消息都是 Claude Code 写的，所有照片是 Flux 生成的，声音是 ElevenLabs 合成的。整个 Maya 只是他 MacBook 里四个 .md 文件。

以前造一个 AI 虚拟网红要花半年甚至一年半，现在只需要4个星期，下一个可能就是一个周末。

作者详细写了 Maya 的四个文件：
persona.md 写她完整的人设、背景、喜好；
voice.md 锁声音风格；
flux.md 固定长相和拍摄风格；
brain.md 记录每个订阅者的记忆和互动历史。
Claude Code 每次回复前都会读这四个文件，从不崩人设，也从不忘记粉丝说过什么。

真的很感慨，技术栈已经简单到可怕的地步。

以前的 Aitana López 花了18个月，现在 Maya 4周就跑通了。

这已经不是科幻，而是任何一个有 laptop 的人都能复制的路径——从 OnlyFans 到 Instagram、TikTok、Twitch，随便哪个平台都能套。

AI 让“虚拟人”成本降到了几乎为零，剩下的唯一瓶颈，是你有没有那个 taste 去决定这个虚拟人要成为什么样子。