Nelly retweeted
This is starting to look genuinely terrifying
I managed to launch 400 agents in Cloud Code in parallel and connected them to a verification layer so that none of them could trick the system
A live control panel is open right before my eyes:
Four hundred digital assistants write and test code simultaneously
The accuracy of every output is verified against the source in roughly 100 milliseconds
After three passes across 100 company profiles, zero errors remain
All final data drops directly into the Obsidian vault
The trick lies in task division: one model does the heavy lifting, while a cheaper one determines whether the statements are true. The loop does not stop until everything is verified
A team of analysts would charge weeks worth of work for this. It completed the job in a single run
This is the exact same "Second Brain + Swarm" pattern that keeps circulating
Bookmark this for the full breakdown
Nelly retweeted
50 Web Sites Google Doesn't Want You to Know About
1.) '12ft.io' — Bypass any paywall
2.) 'libgen.is' — Millions of free textbooks
3.) 'sci-hub.se' — Free academic articles
4.) 'alternativeto.net' — Find free app alternatives
5.) 'justwatch.com' — Find where any content is published
6.) 'archive.org' — Access any old web page
7.) 'gutenberg.org' — 70,000 free classic books
8.) 'pdfdrive.com' — Free PDF downloads
9.) 'openculture.com' — Free courses from top universities
10.) 'wolframalpha.com' — Solve any math problem instantly
11.) 'photopea.com' — Free Photoshop in your browser
12.) 'squoosh.app' — Compress any image for free
13.) 'remove.bg' — Remove image backgrounds for free
14.) 'cleanup.pictures' — Remove objects from photos
15.) 'unscreen.com' — Remove video backgrounds
16.) 'carbon.now.sh' — Turn code into art
17.) 'ray.so' — Stylish code screenshots
18.) 'shots.so' — Free product mockups
19.) 'smartmockups.com' — Create mockups without Photoshop
20.) 'haveibeenpwned.com' — Check if you've been hacked
21.) 'virustotal.com' — Scan any file for malware
22.) 'privnote.com' — Send self-destructing messages
23.) 'temp-mail.org' — Instant disposable email
24.) 'file.io' — Auto-deleting file sharing
25.) 'archive.ph' — Permanently save any web page
26.) 'similarsites.com' — Find alternatives to any site
27.) 'radio.garden' — Listen to any radio station worldwide
28.) 'everynoise.com' — Discover every music genre
29.) 'tunefind.com' — Find songs from any TV show
30.) 'musicforprogramming.net' — Focus music
31.) 'mynoise.net' — Custom focus soundscapes
32.) 'coffitivity.com' — Cafe sounds that boost productivity
33.) 'elicit.org' — AI academic paper assistant
34.) 'consensus.app' — Search scientific consensus
35.) 'connectedpapers.com' — Visualize academic paper maps
36.) 'semanticscholar.org' — Free academic search
37.) 'scispace.com' — Understand any academic paper
38.) 'summarize.tech' — Summarize any YouTube video
39.) 'phind.com' — AI search engine for developers
40.) 'regex101.com' — Test any regex instantly
41.) 'codebeautify.org' — Format code cleanly
42.) 'jsonformatter.org' — Read JSON like a human
43.) 'explainshell.com' — Understand terminal commands
44.) 'raindrop.io' — Effective bookmark manager
45.) 'downdetector.com' — Check if any site is down
46.) 'tineye.com' — Reverse image search
47.) 'fast.com' — Check internet speed
48.) 'smallpdf.com' — Free PDF editing
49.) 'ilovepdf.com' — Merge and split PDFs
50.) '10minutemail.com' — Second-long temporary email
The internet is much bigger than what Google shows you.
Cc : Respective author
Follow me @Bhanusinghyede for more.
This guy used Grok Bot to build a Quant Stochastic system and it made $3,166 a day on Polymarket
The result is already +$427,430 PnL in 135 days with about $245 per average trade, repeating the same setup 31 times every hour across BTC "Up or Down" markets
Several AI agents work together as one algorithm:
1. Stochastic shows where BTC is trading inside its recent range
The bot compares the current level with the highest and lowest levels reached over the recent window:
%K = (Close - Lowest Low) / (Highest High - Lowest Low) × 100
A high %K means BTC is holding near the top of its recent range
A low %K means it is holding near the bottom
This gives the system a simple way to tell whether short-term momentum is leaning toward Up or Down
2. The Signal Line confirms whether that momentum is actually continuing
The bot smooths the fast Stochastic reading:
%D = SMA(%K, 3)
Then:
%K crosses above %D → stronger Up signal
%K crosses below %D → stronger Down signal
Instead of reacting to one extreme reading, the bot waits until the fast signal and its smoothed confirmation move in the same direction
This is the first agent that will create a trading bot strategy for you and then build it:join.horizon.trade/Quant
This trader’s Polymarket account: bosona
Most profitable trades:
$806 → $3,234 (+$2,428)
$657 → $2,708 (+$2,051)
$598 → $2,611 (+$2,014)
The system uses Stochastic to detect where momentum is building and the Signal Line to confirm that the move is still developing
Nelly retweeted
8 free UI inspiration sites for Designers
1. mobbin.com
2. details.so
3. 60fps.design
4. navbar.gallery
5. cta.gallery
6. 404s.design
7. before.click
8. curated.design
What did I miss?
Nelly retweeted
RIP Bloomberg Terminal.
i just reverse-engineered a Bloomberg-style terminal using REA MCP (Reverse Engineer Anything), software got nuked
now i am using $24K/year worth terminal for completely FREE
here is how to reverse engineer the terminal with your AI agents from scratch:
→ install REA and connect its MCP to Claude Code to investigate authorized software & trace how features work
→ map the terminal's core workflows: security search, market quotes, financial statements, news, charts and portfolio analytics
→ build independent data connectors for equities, crypto, forex, commodities and macroeconomic data using documented APIs
→ use opus 5.5 to build the terminal UI, live-data pipelines, historical databases and multi-asset charting engine
→ add financial screeners, yield curves, factor models, portfolio analytics and a Python strategy backtesting engine
→ connect Bloomberg BLPAPI only with the required access and permissions; REA does not unlock Bloomberg's proprietary data for free
→ test every module, verify data accuracy, track licensing rights and ship a working terminal instead of a static UI mockup
if you want to TRY Bloomberg-style terminal, you will find it in the article below:
Nelly retweeted
ESTO ES JODIDAMENTE INCREÍBLE
un dev, él solo, acaba de liberar una alternativa 100 % GRATIS a ElevenLabs que funciona entera en tu propio ordenador.
el repo ya va por las 19.400 estrellas en GitHub.
con él puedes:
→ clonar una voz a partir de un clip limpio de referencia
→ doblar cualquier vídeo a 646 idiomas
→ crear audiolibros, dictar y transcribir
→ escoger entre 14 motores TTS, no solo uno
ElevenLabs llega a 32 idiomas. esto, a 646.
sin pagar por carácter. sin límites de uso. tu audio nunca sale de tu ordenador.
guárdatelo para luego 🔖
repo abajo 👇
I asked Opus 5.5 to explain camera focus by building an interactive lens lab
Here's what it came up with after 1 hour 26 minutes in one shot, $25.66 API cost
lens.lab.sael.net
Move the focus ring and you can see the glass elements shift the sharp plane through the scene
OPUS 5.5 + DOTS + JEV built an armed trading bot in 60 minutes for $6.80
three agents, 1.45M tokens, and the bot had a cap, a stop and a kill switch before its first order
rules → data → backtest → armed
Dario's Opus 5.5 writes the strategy and the risk rules
Dots pulls and cleans four years of candles
Jev backtests it, sets the caps and is the only one allowed to send an order
six switches flip one after another: strategy spec, data, bot code, backtest, paper trade, caps and kill switch. only the sixth lets it trade
Jev holds three limits: a $2,000 daily loss cap, a 4% max position and an armed kill switch
the backtest replayed 1,840 trades over four years. 58% green, 31% a year, worst drawdown -22%
then fees, spread and slippage eat 45% of that, and 31% on paper becomes 17% in life
at 17% a year, $100,000 a month needs $7.06M of capital
so the $100k comes from the capital, and the bot only cost $6.80
not one live dollar has traded yet. sixty minutes proved the bot runs, whether it earns is still open
60 minutes, $6.80, three agents, zero live trades ↓
Nelly retweeted
this is where GPT-6 Astra is getting f...cking illegal
10 open-source GitHub repos I'd use to build the system around the model
01 PydanticAI
▸ github.com/pydantic/pydantic…
→ typed agents + structured outputs
02 LangGraph
▸ github.com/langchain-ai/lang…
→ state + long-running agent workflows
BUILD THE AGENTS
03 Agno
▸ github.com/agno-agi/agno
→ agents + teams + workflows
04 smolagents
▸ github.com/huggingface/smola…
→ agents that execute through code
GIVE THEM MEMORY
05 Mem0
▸ github.com/mem0ai/mem0
→ persistent agent memory
06 Graphiti
▸ github.com/getzep/graphiti
→ temporal knowledge graphs
GIVE THEM A RUNTIME
07 E2B
▸ github.com/e2b-dev/E2B
→ isolated sandboxes for AI-generated code
08 Daytona
▸ github.com/daytonaio/daytona
→ infrastructure for running agent workloads
TEST EVERYTHING
09 DeepEval
▸ github.com/confident-ai/deep…
→ evals for LLM systems
10 Langfuse
▸ github.com/langfuse/langfuse
→ traces + evals + production monitoring
the flow:
request → agent → memory → tools → runtime → eval → retry → deploy
that's the part people underestimate
the model is one folder
the system around it is the product ⭣
GitHub is becoming f...cking dangerous for AI agents
10 open-source repos that turn one powerful model into an entire autonomous system
01 LangGraph
▸ github.com/langchain-ai/lang…
→ stateful agent orchestration
02 PydanticAI
▸ github.com/pydantic/pydantic…
→ typed agents + structured outputs
BUILD THE CONTROL LAYER
03 Mastra
▸ github.com/mastra-ai/mastra
→ agents + workflows + memory
04 Agno
▸ github.com/agno-agi/agno
→ multi-agent systems
GIVE IT CONTEXT
05 Cognee
▸ github.com/topoteretes/cogne…
→ data → knowledge → agent memory
06 Graphiti
▸ github.com/getzep/graphiti
→ knowledge that changes over time
GIVE IT A COMPUTER
07 Browser Use
▸ github.com/browser-use/brows…
→ AI agents that operate websites
08 E2B
▸ github.com/e2b-dev/E2B
→ isolated environments for execution
KEEP IT ALIVE
09 Langfuse
▸ github.com/langfuse/langfuse
→ traces + evals + observability
10 DeepEval
▸ github.com/confident-ai/deep…
→ test agent behavior before production
the architecture:
model → context → planner → memory → tools → execution → eval → retry
that's the shift happening on GitHub
the best repos aren't making another chatbot
they're building everything the model needs around it ⭣
Nelly retweeted
this Jev trading bot turned $1,000 into $3,847 in a simulated DEX run with an average trade of just $13 and a 47% win rate.
I analyzed its decisions with Claude and found the interesting part wasn’t the win rate.
it was how little thinking each trade needed:
> market data comes in
> Jev picks LONG / SHORT / HOLD
> confidence changes -> position changes
> code executes the order
Claude handles the deeper analysis and strategy.
Jev sits inside the fast loop making the tiny calls over and over again.
so instead of:
market -> Claude -> long analysis -> trade
you get:
market -> JEV decides -> code trades
that’s the interesting part.
Claude thinks. Jev makes the call. Code executes.
full Jev setup and cases below
Nelly retweeted
Yesterday @coderabbitai didn't just host a hackathon, it was a Jevathon!
Tired of having to think like a robot? Our favorite hacker review was: "Think like a programmer again" with @allietheicon
1/ Yesterday we hosted @typesafeai at our @coderabbitai HQ for Jev's first ever hackathon!
160+ builders. ~4hrs of hacking. Expert judges, Incredible energy.
I also got to sit down with @allietheicon and talk about what Jev means for Coding, Software Development and the new paradigm shift you have to adapt when working with this new class of AI models.
She shared some really helpful tips and examples of how to best work with Jev - I'll try my best to summarize some of them in this thread⬇️
Nelly retweeted
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
Nelly retweeted
This would take Pixar 2 years to make. With AI, it took me 2 hours.
Script: Sherpa by Pocket FM
Video: Seedance 2.5
Nelly retweeted
THEY JUST LAUNCHED AN AGENT THAT IMPROVES ITSELF.
Here's how Reef works:
→ One single command
→ The agent retrains itself
→ Adds Jev as a tool
→ Searches "Self-evolving Agents"
You don't configure agents anymore.
They evolve.
🤝 Paid partnership
🔥 Jev is on fire!
😎 So we ask Reef: /reefine add jev as a tool
Reef then evolves the agent, and adds Jev into its harness.
We use this evolved agent to hunt for papers related to "Self-evolving Agents" published in 2026 on arXiv. The agent found and screened 120 papers in 9 seconds!
Come and use Reef to evolve your agent: github.com/Human-Agent-Socie…
Nelly retweeted
ESTO ES JODIDAMENTE INCREÍBLE
un dev en solitario acaba de abrir el código de un reemplazo 100% GRATIS de ElevenLabs que se ejecuta completamente en tu propia máquina.
el repo de GitHub está en 19.4K estrellas.
te permite:
→ clonar una voz desde un clip de referencia limpio
→ doblar cualquier video a 646 idiomas
→ generar audiolibros, dictado, transcripción
→ elegir entre 14 motores TTS en lugar de uno
ElevenLabs soporta 32 idiomas. esto hace 646.
sin cobro por carácter. sin límites de uso. ningún audio sale nunca de tu computadora.
guarda esto para después.
os dejo el repo abajo
Nelly retweeted
Replying to @bearableguy123
These codes often show up in the puzzles
gvoeEyPePajzjwjsUx5w5usF5
WhbueMU55AnVr
TUb9y5umtUdx70YfrTsw
Nelly retweeted
#BTC is in long term sell zone price. I don't care if you get mad seeing this tweet. I will always see objectively .
This quoted post is unavailable.
Nelly retweeted
GPT-6 Astra builds the most powerful trading agents
i wrote a 6-page research paper on exactly how to find profitable strategies 24/7 with Astra, along with the COMPLETE CODEBASE
here is how you set it up:
1. the 4 mispricing categories every hedge fund actually hunts (statistical arbitrage, volatility surface, factor decomposition, insider clusters) with the exact formulas for each
2. the 8 bot architecture that maps to every function of a real fund, one bot per role, with maker checker separation so nothing grades its own output
3. the 300 agent monitoring layer that watches order books, options flow, SEC filings, macro releases, and central bank X accounts in parallel
4. the hypothesis generator that reads filtered candidates and codes new strategies every night in Python, backtests them, and throws out anything below Sharpe 1.5
5. the exact validation thresholds every strategy has to pass before deployment. Sharpe above 1.5, drawdown below 15%, hit rate above 55%, t stat above 2.0
6. the Telegram alerts that ping your phone with instrument, strategy, confidence score, Sharpe, drawdown, action window, and Kelly sized position
this is the exact system I have been running for the past 3 days:
Nelly retweeted
hunter biden (@HunterBiden) is about to launch $LAPTOP coin on 9th of September
are we ready for new liquidity drain? 🫡











































