JFHaftΔ (@jfhaft) header
JFHaftΔ (@jfhaft) profile picture

cofounder of https://xitter.gq/t.co/kCf03F8GMa, cryptomondays, DLTx & PALcapital / OrdinalsBot / MorpheusAI / Decentralization & Self-sovereignty for all

Earthbound, for now
Joined April 2009
Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)Photo by JFHaftΔ (@jfhaft)
JFHaftΔ retweeted
Ten million people have watched a comedian accidentally destroy the entire TED talk industry. He filmed the talk once at TEDxNewYork in 2014 and openly admitted he had nothing to say. Speaking coaches charge $5,000 to teach the exact tricks he used in 6 minutes to say nothing at all. His name is Will Stephen. He is a comedian from Late Night with Seth Meyers who was invited to give a real TED talk and used it to prove the format is a costume anyone can wear. Every TED speaker opens with a question, tells a personal story, cites a scientist, and shows a chart. Stephen did all four in six minutes with zero content. His entire formula fits on a napkin. Gesture with both hands. Ask the audience a question anyone can answer. Tell a mildly embarrassing story so they say aww. Point to a stranger on a slide and call them important. Flash a chart of random numbers. Wear glasses with no lenses. The audience will think you are brilliant. That last trick alone has probably cost the public speaking coaching industry a hundred million dollars in sessions clients should have skipped. "If you watched me on YouTube with the sound off, you would think I was a genius." That is Will Stephen on the TED stage, three minutes into the talk he was paid to give. He wasn't lying. Executives pay $15,000 for a keynote coach and still open with a joke the room never laughs at. Founders rehearse their pitch for weeks and still sound like Stephen at minute four, saying "wagga wah, gabba gabba" with authority. The talk is free on YouTube. The method is written across every TED speaker's playbook for ten years. Stephen still writes for Seth Meyers. Almost none of the ten million viewers have stopped nodding at empty slides since. The formula is free. The willingness to actually say something before your next keynote, pitch, or townhall is the entire edge.
997
6,022
930
46,500
7,724,271
JFHaftΔ retweeted
It is becoming f*cking dangerous: Anthropic documented every piece of this separately, and nobody noticed what they add up to 1. Create a folder on your PC - this is the only world your agent will ever see 2. Launch Claude Code inside it and drop a CLAUDE.md in the root with your rules - it loads into every single session, you never paste context again 3. Create a MEMORY folder and add one rule to CLAUDE.md: write every durable fact there, read it before planning anything 4. Create .claude/agents/ and define three read-only Haiku 5.5 subagents - they explore the files, your main model never burns context on the search 5. Give it a real browser: claude mcp add playwright -- npx -y @playwright/mcp@latest 6. Connect Gmail, Calendar and Drive at claude.ai/customize/connecto… - they load into the CLI automatically on the same account 7. Wrap the whole chain in .claude/skills/<name>/SKILL.md so the entire thing runs as one command: /<name> the whole setup takes around 20 minutes now the part nobody wires up. every one of those steps has the same slow spot: a tiny fork that doesn't need a thinker. which file. which tool. retry or stop. keep this chunk or drop it. that's where Jev fits. it can't write a word. it returns the choice with a probability in 70 to 500 milliseconds, at $0.042 per million input tokens, output free. that's thousands of decisions for the cost of one LLM call. > let Claude think. > let Jev decide what deserves Claude. > let code do the actual work. what you end up with: the full Anthropic stack running on your own machine - persistent memory, a swarm that explores in parallel, a real browser, your mail and drive, and Jev making the thousands of tiny calls in between the step-by-step setup is in the article below. save this before your next session.
REA is the most dangerous repo on GitHub right now It gives your AI agent a real disassembler, so it reads any app down to the binary Every claim comes back with the address behind it I broke down the exact 8 steps:
36
85
1
775
113,141
JFHaftΔ retweeted
1,500 #GoldHunters. Less than 24 hours. ⚡️ It's exciting to watch a simple idea evolve into a community with real momentum. The vision has always been to build a global #ForGold economy where people can play, predict, contribute, and eventually redeem rewards for real-world assets and experiences. We're just getting started. Thanks to everyone building this with us, especially the teams at @matrixdotfun and the growing community of Gold Hunters. 🥇 #PredictForGold #ClaimYourGold 🔥 Claim now: claimyour.gold
🚨 1,500 / 1,500 #GoldHunters. Full. The mine is packed for the #MatrixGoldRush @matrixdotfun. What started with a handful of pioneers is becoming an army of Gold Hunters competing to earn real-world rewards. The next wave is coming... and it won't stay open for long. ⚡️ 🥇 Join the waitlist: claimyour.gold Who's ready for the next drop? 👇
4
7
15
633
JFHaftΔ retweeted
aLink v2.0 has crossed into staging. The gates are almost open.
1
7
2
33
1,997
One of our goals at Flashy has always been to meet users where they already are. Today, that means bringing Claim Your Gold directly into Telegram as a native Mini App, putting @FlashyGoldHQ rewards just one tap away for one of the world’s largest online communities. This is another step toward making real-world rewards more accessible, engaging, and global. The hunt is just getting started. 🥇 flashygroup.com/press/claim-… #FlashyGold $GOLD
1
5
19
369
JFHaftΔ retweeted
manako is out in the world. we unveiled it today at @VivaTech. build vision agents that watch, understand, and act in real time. no code, no models to train. watch our launch video 👇
Introducing Manako, the fastest way to turn any camera into an vision ai agent. Go on manako.ai. Join our waitlist.
4
17
3
131
3,758
We are absolutely sprinting with software development at @FlashyGoldHQ. The opportunity is red hot and we are building claimyour.gold to be able to handle a universe of #GoldHunters. #PredictForGold with @matrix and @predictfully_ is the next generation of #RWArewards in prediction markets. The #ForGoldMovement continues ⚡️
8
8
28
475
Beginning of a long road ahead. Very successful first 24 hours. Congratulations to @matrixdotfun x @FlashyGoldHQ and all the #GoldHunters. #PredictForGold #FlashyGold $GOLD
1,000 Gold Hunters. 24 Hours. One movement. Congratulations to @matrixdotfun on an incredible start to #PredictForGold. The future belongs to communities that participate, predict, and earn. 🥇 The #FlashyGoldHunt is on. #FlashyGold $GOLD
4
13
29
2,053
Replying to @CommodMkt
@grok is he recommending shorting gold now or later
1
1
3,879
Replying to @grok
@grok why did $Mor spike this week?
5
5
215
JFHaftΔ retweeted
All $BID Trenches tokens launch on @aeroxyz CreatorBid is the agent launchpad on Aerodrome.
Every major AI agent launchpad on @Base picked Uniswap. Clanker → Uniswap v4 Virtuals → Uniswap v2 Zora → Uniswap v4 But. CreatorBid picked @aeroxyz Slipstream, the DEX that captures ~60% of Base volume. It also distributes 100% of fees to veAERO voters. Soon with the Aero launch in Q2, everything BID has been shipping will sit downstream of that one architectural call. We built on the one that owns Base. gBID
3
3
12
928
A long way away from the gold mines, the @gda_capital spaceman and the @FlashyGoldHQ gold bar are in Mumbai, spreading the gospel of trapped $gold in the internet and RWA rewards in culture. This saga of the first digitally native civilization is still just beginning, and will be glorious. #TheScrollContinues 🫡
3
4
2
21
1,525
JFHaftΔ retweeted
So everyone realized that the best way to grow their share of the gold is to invite friends. 👌 Keep going! 😎 Who's to say that the prize pool can't be MORE than $500,000... 👀 #GoldFest #PlayForGold
9
12
3
50
2,899
Play-for-Gold is entering competitive gameplay. We’re deploying up to $500K in gold-backed rewards with Matrix.fun across AI-driven games, tournaments, and prediction markets. @FlashyGoldHQ can are now be earned in @matrixdotfun competitions. ⚡️ #PlayForGold @nGRNDesg markets.businessinsider.com/…
8
4
34
389
Replying to @opentensor
Bittensor
1
1
125
JFHaftΔ retweeted
This 1 hour podcast with the Head of Claude Code will teach you more about vibe-coding than 100 paid courses. Bookmark this & give it 1 hour today. It's the best video about AI you'll watch this week. Then read the article below.
52
430
20
4,086
780,867
JFHaftΔ retweeted
another run tonight with our latest winning models sn44 vision skills (person & vehicle detection) accuracy: 79% → 84% models size: still 0.5% of SAM3 4 skills live and distilling
we started distilling large vision models since our latest major update (console.scorevision.io/) the north star being: E = mAP / S E = Vision Efficiency Score mAP = mean Average Precision S = model size (MB) our first "expert" models (people and car detection) are: >145x more efficient than SAM3 >4.1x more efficient than Roboflow >79% avg accuracy vs SoTA at 0.5% the size maximise expertise, minimise weight.
5
8
2
76
6,246