Y.

web developer

[Mr. Buzzoni @polydao]

I HAVEN'T OPENED CLAUDE AT MIDNIGHT SINCE I BUILT THIS FOLDER

I used to wake up, check what broke overnight, fix it by hand

-> now I wake up and the receipts are already sitting there, dated, graded, waiting on my review

here's what's actually inside the folder that replaced me:

• the contract
> CONTRACT.md - the shift rules, committed
> contract.local.md - my personal overrides, gitignored

• the harness (.claude/loops/)
> settings.json - spend caps and timeouts I set once
> schedule.yml - when the next shift fires
> rubrics/ - code.md, writing.md, safety.md - the graders that catch what I'd miss
> pr-hunter/ - plan.md wakes it, https://t.co/VUDfqGE1Fp does the actual work

• the state
> receipts/ - one folder per shift, 5,382 kept so far
> trace.log - exactly what happened, no guessing
> checkpoint.json - picks up where the last shift left off

• the edges
> https://t.co/agzjvw6VbF - my panic file, never once used
> .mcp.json - the tools it's allowed to touch

I don't wake up for this anymore. the folder does

[Addy Osmani @addyosmani]

https://t.co/hIe0UX7z6T

[Kirill @kirillk_web3]

instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company

it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale

useful whether you've never built an agent in your life or have been using Claude every day for the past year

I took the key ideas and turned them into a practical guide on how to actually build with Kimi

find it below

[Defileo🔮 @defileo]

https://t.co/XknL2qFBAP

[日本語フリーフォント✒️ @ffontjp]

【商用利用OK】ドットのフリーフォント10選

[Tom Dörr @tom_doerr]

Python library for 43 technical analysis indicators

https://t.co/oJ88ckkI5P

[Tom Dörr @tom_doerr]

Improves Claude Code frontend design with 70+ curated skills

https://t.co/cS1n9T4oBL

[MiddleFinger 💎 @Psolemn]

Volume จะต้องดูทั้ง spot + derivatives(futures, options) ด้วยนะ เพราะ price movement หลายครั้ง driven by leverage

โดยเพชรจะใช้ข้อมูลพวกนี้เพื่อดู

- Spot > real demand/supply
- Futures > leveraged positioning
- Funding rates > crowding ฝั่ง long/short
- (Top traders) Long/Short ratio > positioning skew

เราไม่ได้แค่เห็นแค่ volume แต่เห็น positioning เลยว่า ฝั่งไหนคุมเกม ฝั่งไหน crowded และฝั่งไหนเสี่ยงโดน squeeze(พวก fake breakout ทั้งหลาย) ดูคู่ footprint และ delta เราจะเห็น orders จริงชัดๆเลย อันนี้จริง อันไหน spoofing หรือดูเหมือนกำลัง wash

ตลาดที่ขยับมักเป็นเรื่อง imbalance + forced unwind และมักมูฟจาก liquidity นึง ไปยังจุด liquidity นึงเสมอ เราจึงใช้พวก liquidation heatmap ควบคู่ไปด้วย

พอเอาไปใช้กับ technical การอ่าน price action จะดีขึ้นมากครับ โดยเฉพาะเมื่อเราเรียนกับคนที่รู้เรื่อง participant อย่าง market makers ดีที่สุดคนนึงด้วยแล้ว

เตรียมตัวไปเรียนกันนะครับ

[Tom Dörr @tom_doerr]

Native desktop crypto charting with heatmap and footprint views

https://t.co/nExAgw8qXW

[Tom Dörr @tom_doerr]

AI agent skills for crypto and stock trading

https://t.co/ySCk8K98NP

[AI Will @FinanceYF5]

这个 AI 很强。

LingBot-Map 可以把实时视频流转换成实时的 3D 重建。

20 FPS

代码 + 模型 👇

[GitHub Projects Community @GithubProjects]

Professional-grade quant analytics, AI-powered market research, and economic data tools.

It is a pure C++20 native desktop app delivering Bloomberg Terminal-level market analytics, investment research, and economic data tools, completely open source.

It packs a CFA-level analytics engine with AI automation into a single terminal application that costs $0 instead of $24,000/year.

Explore more:
https://t.co/yNrt5TvLSt

[CyrilXBT @cyrilXBT]

https://t.co/P2lHgWsZ7a

[Marek Jóźwiak @madebyhex]

Big update in Motion GPU - added first-class support for Vue 3 🎉

Now available: React 18/19, Svelte 5, and Vue 3.

Also: interactive playground is now available for all supported frameworks.

Motion GPU - WebGPU, without the noise.

Check it out:
https://t.co/Uloxsg1VK6

[AdiiX @adiix_official]

CHINESE DEVELOPER RECORDED A 2 MINUTE TUTORIAL ON HOW TO SET UP CLAUDE CODE AGENTS AND TURNED $284 INTO 868K

Three monitors behind him.

Messy desk. Cables everywhere. Posted it to Bilibili expecting maybe 100 views.

Bro pause at 0:47. Look at the right monitor.

$868K PROFIT WHAT?

gabagool22.
$868,862 profit.
28,620 predictions.
Joined October 2025.
His profile:

https://t.co/SRpsaLOGRd

Copytrading:

https://t.co/uGhkwLt4cb

He was just filming a simple tutorial about AI agents nothing special. But he overlooked one small detail: his crypto wallet was open on a second monitor.

And for a few seconds, it slipped into the frame.

What people saw didn’t make sense at first.

28,620 trades. All in BTC. Every single one on 15-minute intervals. And somehow… every single one profitable.

The comments quickly turned into an investigation. Someone slowed the video down to 0.25x. Others captured every frame where the second screen appeared.

Piece by piece, they stitched it together rebuilding the entire wallet view from just a few seconds of background footage.

The numbers looked unreal: entries between 2 and 10 cents, exits in the thousands. Line after line glowing green. Not a single loss across tens of thousands of trades.

And it wasn’t just one machine.

It was a system. A whole farm of computers, each scanning different 15-minute windows at the same time. Together, they covered everything nonstop, 24/7.

He deleted the video three hours later.

But by then, it didn’t matter. Someone had already recorded it.

The clip surfaced on Discord. Then spread to Telegram. Then exploded on Twitter.

The original tutorial barely reached 200 views.

The clip of his second monitor? Over 400,000.

Now hundreds of thousands of people are watching that wallet. He hasn’t posted anything since.

But the screens are still running. The wallet is still active. The system hasn’t stopped.

He set out to teach people how to build AI agents.

Instead, he accidentally revealed what his were already doing.

[Lunar @LunarResearcher]

My little brother called me during a lecture.

"I'm not finishing my coursework."

I thought he was dropping out. He's 20. First year of uni.

"I'm building agents instead."

He found an article about 5 agent architectures for prediction markets. Prompt chaining, routing, parallelisation, orchestrator, evaluator.

He built all five. Same model. Same data. Let them run for a month.

"The dumb one made $1,200. The smart one made $4,200."

Same API key. Same markets. The only difference - how the agents talk to each other.

The chained one hit 61%. The parallel one - 73%.

"Which one do you use?"

None of them pure. He routes markets to specialists, then the evaluator kills anything under threshold.

$3,000 gap between the worst and best architecture. On identical inputs.

His professor asked what he's working on.

He said "machine learning project."

Copy the bot here: https://t.co/bOnjwmXEEl

His coursework is worth 30% of his grade.

His agents made more last month than my salary.

He's 20. I'm paying rent.

The evaluator doesn't care about your degree.

[Oliver Prompts @oliviscusAI]

🚨 Someone just open-sourced a full suite for tracking satellites and decoding their radio signals 100% locally.

It uses an SDR to pull weather images and raw data straight from space to your hard drive.

100% Open Source.

[Ihtesham Ali @ihteshamali]

this shouldn't be free.

Vibe-Trading is an open-source AI trading agent that ships with 64 finance skills, 29 specialist swarm team presets, cross-market backtesting, and a full quant analysis toolkit.

The architecture is what makes it different from everything else in this space.

It's not a wrapper around one model with a few finance prompts. It's a DAG-based multi-agent system where specialized agents collaborate, debate, and hand off between each other while you watch the entire reasoning process stream in real time.

You get:

> Technical analysis across Ichimoku, harmonic patterns, Elliott Wave, SMC, and 60+ other setups
> Quant tools: factor IC/IR analysis, quantile backtesting, Black-Scholes, full Greeks, portfolio optimization via MVO, Risk Parity, and Black-Litterman
> Alt data: social sentiment, behavioral finance signals, macro regime detection, sector rotation
> Crypto desk: perp funding basis, liquidation heatmaps, stablecoin flows, DeFi yield, token unlock tracking
> Full CLI with a TUI, a FastAPI web server, and a React frontend

HK/US equities and crypto data are completely free. Docker deploy takes 2 minutes.

https://t.co/lm7xHk3PLF

MIT License. 100% Opensource.

[Hanako @hanakoxbt]

a Citadel intern told me something at a party he probably shouldn't have

it was on a rooftop in brooklyn. i mentioned i trade prediction markets. he got quiet for a second.

"we have a model for that. it scores every contract on four factors. when all four align we enter. when any breaks we exit. that's it"

i asked what the four factors are.

he looked around. then said it fast like he was confessing.

"cross-market divergence. disposition coefficient. capital velocity. pair network correlation"

I didn't know what half of that meant. but i memorized it.

went home. 11pm. opened Claude.

"here are four scoring factors from a quant fund. build a terminal that runs all four on prediction markets"

Claude asked one question: "Where's the data?"

I sent him one repo: https://t.co/bDfn7TyVhG

86 million trades. every wallet. every entry. every outcome

three weeks later i'm sitting in my apartment watching a screen i barely understand print money.

the disposition meter alone changed everything. it measures how you exit - not how you enter.

top wallets capture 86% of winner value and cut losers at 12%.

everyone else captures 58% and holds losers to 41%.

same exact entries. the exits make it a completely different game.

capital velocity: 49x. every dollar gets recycled 49 times before the average trader recycles once.

the terminal found 42 pair correlations across 11 markets. when MSFT beats Q3 is priced at 80c but the model reads 93% - it enters. when the gap closes 2 hours later - it exits.

no opinions. no news. just four numbers that either align or don't.

his fund runs this with a floor of PhDs and $800M AUM.

my setup:
> Claude - $20/month
> VPS - $5/month
> poly_data repo - free
> Polymarket API - free

$25/month. no team. no office. no Bloomberg.

280 trades so far. 70% win rate. $800 seed.

four bots splitting the work:
pulse_alpha +$299.
arb_hunter +$558.
trend_rider +$337.
cal_engine +$719.

+$11,514 total.

copytrade here: https://t.co/PTZuvewZE6

he texted me last week.

"delete everything i told you"

too late.