Dev / Artist / Trader , Web3 Crypto Degen
Joined January 2014
- Tweets20.4K
- Following2.2K
- Followers2.5K
- Likes19.8K
Bongo retweeted
This is f*cking insane. Google just released a free 2-hour course on full Harness engineering, from 0% to 100%:
0:29 - Harness engineering from zero
11:08 - your first agent, built properly
28:08 - Eval engineering with a Chief of Staff agent
1:00:13 - Loop engineering
1:23:19 - a self-improving graph system that never stops
I've seen $500 courses that don't cover what it shows in the first 15 minutes.
Watch it, then go further with the guide below on building a system that improves itself.
Bongo retweeted
Medical marijuana has an amazing effect on this guy with Parkinson’s disease
And the side effects? The munchies
Writer: Ian
Bongo retweeted
🚨BREAKING: SOLANA PROCESSED MORE TRANSACTIONS THAN ALL OTHER CHAINS COMBINED!🚨
Solana handled 113.8M transactions in 24 hours.
The next 9 biggest chains did 89.6M together, and Sui came second at 25.37M.
Bongo 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
Bongo retweeted
Jev builds the MOST POWERFUL trading agents
and someone JUST open sourced jev-trader, a fully working 24/7 trading bot with Jev
along with COMPLETE low latency CODEBASE
WHAT THIS MEANS FOR YOU - you no longer have to build a trading bot with Jev from scratch, you just clone this and make it yours
here is how you make your own Jev trading bot with this repo:
1. clone it and run three commands, it boots straight into dry run mode with real book data, real decisions, and simulated fills so you can watch it think with zero capital
2. drop in your Jev API key and the model starts answering buy or sell on every block with calibrated probabilities in 81 milliseconds
3. swap the book reader for your own venue, the model interface is clean so any order book that returns bids and asks plugs straight in
4. tune the decision cadence and horizon, ask the model every N blocks about the move over the next M, so you control how aggressive the engine trades
5. the hot loop already fits one block with exactly two round trips, one to read the book, one to send the order, nothing else on the path, this is the institutional latency discipline most retail bots never reach
6. plug in the live server and every block, every decision, every fill streams to a public dashboard so you watch your engine run
the whole point is this repo hands you HARDEST part for FREE -
> the low latency engine
the COMPLETE breakdown of how i turned this into hedge fund grade HFT trading system is in my article below:
Bongo retweeted
🇺🇸 TRUMP DOESN’T WANT AI TO SLOW DOWN.
@kyledoops says the AI arms race is only getting hotter as Trump pushes back on safety driven calls to pump the brakes.
“The arms race in AI does continue.”
Bongo retweeted
🚨BREAKING: SOLANA’S PROPOSAL TO DOUBLE ITS DISINFLATION RATE OFFICIALLY PASSES BY A RAZOR-THIN MARGIN!!!🚨
Bongo retweeted
Here's an early game trailer of Cook the Dungeon (🔊Sound on), a first-person roguelike deckbuilder where you defeat monsters, harvest their parts, and cook meals for the battles ahead.
If the game interests you, please wishlist the game on Steam! It helps the game to get discovered.
Bongo retweeted
Prompt without missing a beat with HUD Mode
so you can play WoW and prompt now w/ Hermes HUD mode
it's a seamless overlay where you can keep an eye on things or ask questions about a game during your session.
@NousResearch
Bongo retweeted
BREAKING: AUTO is live on Solana, backed by U.S. auto loans.
Consumer lending is the largest credit market in the U.S., and AUTO brings near-prime auto yield onchain for the first time.
AUTO is officially live on Solana.
• Backed by U.S. auto loans originated by Agora
• Delivered to DeFi through @Figure Forge
• Looping/lending strategies now available across @kamino
• Vault curation by @SentoraHQ ; market making via @RockawayX
• Powered by @Chainlink Data Streams
From a single asset that redefined an RWA category, to a multi-asset marketplace for onchain yield.
Bongo retweeted
Andrew Ng just dropped a 3-hour course on how to become an AI Engineer in 2026:
• 00:00 - How to build agentic AI systems
• 04:25 - Future of AI engineering
• 23:38 - AI Prompting full course
• 2:52:17 - Creating an app with AI in 30 minutes
This 3-hour watch could replace 10 AI engineering courses on the internet.
Watch it today, then read how to run a self-improving system in the article below.
Bongo retweeted
My friend applied to 250 tech jobs in two years. No MIT. No Stanford. No PhD.
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 4-hour course on "How to build a full LLM from scratch."
Anthropic's own researcher gives up the exact playbook behind building LLMs like ChatGPT & Claude.
I watched it last night.
Halfway through, I realized I could break into an AI lab in months, not years.
Bookmark this and read the article below.
• 00:00 - LLMs as new OS
• 40:58 - LLM tokenization architecture
• 53:22 - LLM neural network internals
• 1:04:20 - LLM pretraining
• 3:21:37 - LLM RLHF & DeepSeek R1
Bongo retweeted
30 GitHub repositories every AI developer should bookmark in 2026. 🤖
If you're building with AI, these repositories belong in your toolkit.
1. OpenHands — AI software engineer
→ github.com/All-Hands-AI/Open…
2. LangChain — build LLM apps & agents
→ github.com/langchain-ai/lang…
3. Dify — open-source AI app platform
→ github.com/langgenius/dify
4. Browser Use — AI browser automation
→ github.com/browser-use/brows…
5. Firecrawl — convert websites into LLM-ready data
→ github.com/mendableai/firecr…
6. Mem0 — memory for AI agents
→ github.com/mem0ai/mem0
7. CrewAI — multi-agent framework
→ github.com/crewAIInc/crewAI
8. AutoGen — Microsoft's AI agent framework
→ github.com/microsoft/autogen
9. Open WebUI — ChatGPT-style interface
→ github.com/open-webui/open-w…
10. Langflow — visual AI workflows
→ github.com/langflow-ai/langf…
11. LlamaIndex — connect LLMs to your data
→ github.com/run-llama/llama_i…
12. Ollama — run LLMs locally
→ github.com/ollama/ollama
13. vLLM — high-performance LLM serving
→ github.com/vllm-project/vllm
14. llama.cpp — run LLMs on almost any device
→ github.com/ggml-org/llama.cp…
15. Transformers — Hugging Face ML library
→ github.com/huggingface/trans…
16. ComfyUI — node-based AI image generation
→ github.com/comfyanonymous/Co…
17. Continue — AI coding assistant
→ github.com/continuedev/conti…
18. Aider — AI pair programmer
→ github.com/Aider-AI/aider
19. GPT Researcher — autonomous research agent
→ github.com/assafelovic/gpt-r…
20. Crawl4AI — web crawling for AI & RAG
→ github.com/unclecode/crawl4a…
21. Bolt.diy — build AI apps locally
→ github.com/stackblitz-labs/b…
22. LocalAI — self-host OpenAI-compatible models
→ github.com/mudler/LocalAI
23. AnythingLLM — private AI workspace
→ github.com/Mintplex-Labs/any…
24. Flowise — drag-and-drop LLM builder
→ github.com/FlowiseAI/Flowise
25. Open Interpreter — let AI run code
→ github.com/OpenInterpreter/o…
26. DeepSeek — official open-source AI models
→ github.com/deepseek-ai
27. Lobe Chat — modern AI chat interface
→ github.com/lobehub/lobe-chat
28. RAGFlow — enterprise RAG framework
→ github.com/infiniflow/ragflo…
29. MarkItDown — convert documents to Markdown
→ github.com/microsoft/markitd…
30. n8n — AI-powered workflow automation
→ github.com/n8n-io/n8n
Bookmark this.
Which repo are you trying first? And which one did I miss? 👇
Bongo retweeted
FABLE 5 has been extended again until July 19… and I just found one of the wildest AI trading wallets I’ve ever seen. 🤯
This trader used Claude Fable 5 to improve a Quant bot that reportedly generated +$288,872 on prediction markets.
Since April 30, the bot has averaged roughly $6,878 in daily profit, executing around 30 trades per hour in short-term Bitcoin Up/Down markets.
📊 42 Days Performance
• 30,670 predictions
• 56% win rate
• Thousands of automated trades
The strategy isn’t complicated:
→ Wait for short-term market prices to deviate from fair value
→ Enter before prices fully readjust
→ Repeat the same high-probability setup over and over
→ The edge isn’t one massive trade—it’s consistent execution at scale
Some standout trades:
💰 $2,851 → $7,332 (+157%)
💰 $881 → $4,756 (+439%)
💰 $3,455 → $6,319 (+83%)
With Claude Fable 5, some estimates suggest systems like this could scale even further:
🚀 ~$6,878/day → ~$15,927/day
🚀 Potentially $1M+ per month under ideal conditions
Whether those projections hold up in real markets is another question—but it’s a fascinating example of how AI is changing algorithmic trading.
✅ Prompt pack
✅ Quant bot setup
✅ Automation guide
✅ Best AI tools I use
To enter:
1️⃣ Like ❤️ this post
2️⃣ Repost 🔁
3️⃣ Comment “FABLE” below
I’ll randomly pick winners after the giveaway ends.
#AI #Claude #Anthropic #Bitcoin #Trading #Polymarket #Crypto
Bongo retweeted
ChatGPT + Claude + internet connection + 60 minutes a day = $8,400 per month.
Usually, I charge $97 for this guide, but today you get it 100% for free.
Like + comment 'Send' and I'll send you my step-by-step guide for FREE.
Must follow me to get guide in DM.
FREE for 48 hours.
Bongo retweeted
/ THE BOX IS LIVE /
Now every burn also opens a box
MAIN ROLL: a Haxz, an unstake pass, or a free trait re-roll
BONUS ROLL: (@BoredApeSolClub · @MidEvilsNFT · @LoudLordsNFT · @misfitsorder · @MicrosNft ) or a SOL drop (0.1 / 0.25 / 0.5)
HIGH WIN
haxz.xyz/box
Bongo retweeted
THIS GUY BUILT A JARVIS THAT HELPS RUN AN $11,500/MONTH BUSINESS:
4 clients. 847 active users. 23 new leads. 4 calls booked. 3.8x return on ad spend.
and it reports everything out loud in under 60 seconds.
JARVIS checks revenue, monitors the community, finds prospects, drafts personalized emails, updates the calendar and pauses the weakest ads.
This isn't a voice assistant.
It's an AI operator that can run the repetitive parts of a business while you focus on decisions.
The voice was just step one.
Add memory, email, calendar, analytics and automations, and JARVIS becomes a digital employee that works even when your laptop is closed.
You can start with the part that talks.
Mine takes 30 minutes and costs about $4 a month.
The full build is below.
Bongo retweeted
instead of watching 2 hours of Netflix tonight, watch this Stanford lecture
it's the clearest explanation I've seen of how ChatGPT and Claude actually work
useful whether you've never touched AI in your life or have been using it every day for the past year
I took the key ideas and turned them into a practical guide on how to actually get 100% out of Claude
find it below
