Micro/M43

19.9K posts

Micro/M43 banner
Micro/M43

Micro/M43

@MicroM43

Streaming thoughts, editing chaos || Building on-chain identity & interactive connections for real-world products | Reshaping ownership & commerce @kinnectibles

Boston, MA เข้าร่วม Aralık 2009
3.9K กำลังติดตาม5K ผู้ติดตาม
ทวีตที่ปักหมุด
Micro/M43
Micro/M43@MicroM43·
I have 15 years experience in unique item serialization and digital product identifiers for footwear, apparel and luxury brands. Plus 4 years working on decentralized commerce platforms in #web3 and NFTs. #AMA
English
22
10
184
18.7K
Peter Girnus 🦅
Peter Girnus 🦅@gothburz·
My net worth peaked at $1.2 million. None of it was real. I don't mean that philosophically. I mean it was located on servers that have since been turned off. I own eleven properties in the metaverse. Three in Decentraland. Four in The Sandbox. Two in Voxels. One in Otherside. And a beachfront villa in Horizon Worlds that I bought for $214,000 because Mark Zuckerberg called it "the next frontier." The frontier closed last week. It's a mobile app now. Last year I mass DM'd 340 people the phrase "you don't understand how early we are." I have since stopped doing that. Not because I was wrong. Because most of them blocked me. I got into metaverse real estate in November 2021. Everyone was buying. Someone paid $450,000 to be Snoop Dogg's neighbor. In a video game. With no legs. The avatars didn't have legs. I thought that was bullish. "The legs are coming," I told my Discord. "Legs are a roadmap item." Three hundred people reacted with rocket emojis. I called myself a "digital land baron." I put it in my Twitter bio. I put it in my LinkedIn headline. I said it on a podcast that had eleven listeners. Three of them were bots. The rest were my alts. My virtual property has more square footage than my actual apartment. My actual apartment has furniture. Location, location, location. My most valuable asset was a plot next to a virtual Gucci store. Gucci left in 2023. The store is still there. Nobody's in it. It's like a mall in Ohio but with worse graphics and no food court. I held. Diamond hands. That's what we said. "Diamond hands." It means refusing to sell while your investment loses 94% of its value. We turned financial paralysis into a personality trait. A guy in my Discord paid $2.4 million for a 618-parcel estate in Decentraland. Prime district. High foot traffic. I asked him what "foot traffic" meant when the platform had 38 daily active users. He said I didn't understand the technology. I didn't. I still bought more. We had a DAO. A decentralized autonomous organization. That means we voted on decisions. There were nine of us. Three never showed up. Two voted on everything without reading it. The other four were me and my alts. We voted to "acquire strategic parcels." The vote passed unanimously. I voted four times. My portfolio peaked at $1.2 million. I told everyone. I made a spreadsheet. I projected 40x returns by 2025. I made a pitch deck. The pitch deck had a slide that said "WE ARE BUILDING THE DIGITAL ECONOMY." The slide had a rocket emoji. That was my entire financial model. In 2023 I bought a Bored Ape for $189,000. It's worth $14,000 now. I don't talk about the Ape. I still use it as my profile picture. People ask me about it. I say "I'm long-term bullish." Long-term bullish means I can't sell it without crying in a Panera. My mom asked me what a Bored Ape was. I said "digital art on the blockchain." She asked why it cost more than her car. I said "you don't understand Web3." She said "I understand you live in a studio apartment." She's not in my Discord. Justin Bieber bought one for $1.3 million. It's worth about $90,000 now. I felt better about mine after I heard that. That's community. WAGMI. We're All Gonna Make It. We said that every day. In the group chat. While the floor dropped. While the volume dried up. While 95% of all NFT collections went to zero. We're all gonna make it. None of us made it. But we said it with conviction and a laser-eye profile picture. That counts for something. It doesn't. But we said it did. That's decentralized consensus. Meta spent $84 billion on the metaverse. I need to say that again. $84 billion. More than the GDP of Luxembourg. More than the GDP of Iceland, Luxembourg, and Malta combined. They spent it on a platform where the avatars had no legs, the graphics looked like a 2006 Wii game, and the peak user count was lower than the lunch rush at a Chipotle in Des Moines. They just pulled Horizon Worlds from VR headsets. It lives on as a mobile app. My beachfront villa is now a mobile app. Location, location, location. Zuckerberg renamed the entire company for this. Facebook became Meta. A $900 billion company changed its legal name because the CEO watched Ready Player One and said "I want that." Reality Labs lost $10 billion in 2021. $14 billion in 2022. $16 billion in 2023. $18 billion in 2024. $19 billion in 2025. That's not a strategy. That's a speedrun. They laid off 1,500 Reality Labs employees this year. Shut down three VR studios. Killed Supernatural. Put the entire VR social vision in a casket and said "we're pivoting to AI and wearables." The pivot took four years and $84 billion. I pivoted too. I'm an AI real estate investor now. I bought a virtual plot in an AI-generated world that doesn't exist yet. The founder said it was "the intersection of spatial computing and large language models." I don't know what that means. I gave him $40,000. He has a whitepaper. It's 47 pages. I read the title and the tokenomics section. The tokenomics section is a pie chart. I love pie charts. They make everything look like a plan. The project has a roadmap. Q1: "Build community." Q2: "Launch beta." Q3: "Scale ecosystem." Q4 is blank. Q4 is always blank. That's where the exit scam goes. My accountant asked me to value my metaverse portfolio for tax purposes. I said $1.2 million. He said "current market value." I said $6,400. He stared at me for eleven seconds. I know because I counted. He asked if I had any other investments. I showed him my NFTs. He stared for longer. I told him they were "cultural artifacts with long-term provenance." He asked if I'd considered a 401k. I told him a 401k was "legacy finance." He told me to leave his office. The metaverse is dead. I don't accept that. I am a digital land baron. I own eleven properties across four platforms. I have a beachfront villa in a mobile app, a plot next to an empty Gucci store, and a cartoon monkey that cost me more than my actual car. Location, location, location. The location is nowhere. But I'm early. I'm always early. That's the same as being wrong except you get to say it with confidence.
English
1.7K
1.2K
9.8K
1.7M
Micro/M43
Micro/M43@MicroM43·
🎙 CHANGING ON THE FLY - EP. 2 Agents, Opportunities, and Outcomes Five builders. Different stacks. Same pattern: the model isn’t the product. We’re breaking down: • agent architecture • memory (CLMP) • content pipelines • real-world systems that actually work 🗓 Thursday ⏰ 1:00pm EST Next shift coming 👇🏻
Micro/M43 tweet media
English
6
0
9
309
Long Lost
Long Lost@LongLostNFT·
gm everyone who is ready to join us at 10 pm est?
Long Lost tweet media
English
26
17
67
904
dustin
dustin@pyra_m1d·
Five builders comparing notes and finding the same pattern across completely different stacks. The LLM model is not the product. What you wire around it is. This Thursday we're showing what's actually running. Not hype. Not theory. Live systems doing real work. Agent architecture. Memory that persists. Pipelines that ship content while you sleep. Pull up a chair.
Micro/M43@MicroM43

🎙 CHANGING ON THE FLY - EP. 2 Agents, Opportunities, and Outcomes Five builders. Different stacks. Same pattern: the model isn’t the product. We’re breaking down: • agent architecture • memory (CLMP) • content pipelines • real-world systems that actually work 🗓 Thursday ⏰ 1:00pm EST Next shift coming 👇🏻

English
1
0
1
53
Maaaaahhhaaaaa 👁️
Maaaaahhhaaaaa 👁️@Maaaaahhhaaaaa·
Can’t wait for Roundtable today! We will be chatting about our future title, season 2 of the hub, IRL events, and whatever else is on the community’s mind 🍗✨
Maaaaahhhaaaaa 👁️ tweet media
English
19
14
79
1.1K
Micro/M43
Micro/M43@MicroM43·
@zubic_eth Feature not a bug. I’d say they are winning the engagement game quite well.
English
0
0
2
16
Micro/M43
Micro/M43@MicroM43·
The funny part is, GPT told me to say that… 👇🏻 You’re describing a model that shows up a lot in modern platforms—there isn’t just one name for it, but it generally falls into a few overlapping concepts: ⸻ 🧠 The Core Idea A system where: •The user pays (or participates as a customer) •While also generating the core value/data/labor •Which the platform then captures, structures, and monetizes ⸻ 🏷️ Common Terms for This 1. Prosumer Model •“Producer + Consumer” •Users both consume the service and create the content/data •Classic examples: •Social media (you post → they monetize) •Marketplaces (you list → they take fees) 👉 But this doesn’t fully capture the data extraction angle. ⸻ 2. User-Generated Data Capture (UGC + Data Exhaust) •The system is designed so: •The act of using the product generates valuable data •Often called: •Data exhaust •Behavioral data capture •Example: •Using a fitness app → your workouts train their models ⸻ 3. Human-in-the-Loop Systems •Users are unknowingly (or knowingly) doing labeling, validation, or training work •Especially relevant in AI: •CAPTCHA → training vision models •Feedback loops → improving LLMs ⸻ 4. Play-to-Earn / Work-to-Play Hybrids •Popular in Web3 framing •Users: •Pay (buy assets, tokens) •Then perform actions that create ecosystem value •Often blurred with: •Gamification •Speculation ⸻ 5. Crowdsourced Labor Platforms (Disguised or Explicit) •Users effectively do labor at scale •Sometimes: •Paid (Mechanical Turk) •Unpaid (most platforms) ⸻ 6. Two-Sided Value Extraction Platforms (closest to what you’re hinting at) •Platform monetizes: •Access (user pays) •Output (user-generated data/work) •This is the cleanest framing of what you said ⸻ 🔥 The Sharpest Way to Phrase It If you want something punchy / concept-level: “Pay-to-produce data systems” or “User-funded data extraction platforms” or (more philosophical) “Inverted labor markets where the worker pays to work” ⸻ 🧩 Real-World Examples •Duolingo •Users learn → also generate translation data (historically) •Roblox •Users pay → build worlds → platform monetizes •OpenAI / AI tools broadly •Users pay → generate usage data → improves models •Trading platforms •Users pay fees → generate market data/liquidity ⸻ 🧠 Why This Model Wins •Infinite scalability of labor •Built-in incentives (fun, utility, profit) •Data flywheel: •Use → Data → Better product → More users → More data ⸻
English
1
0
1
15
NewsForce
NewsForce@Newsforce·
POKÉMON GO PLAYERS TRAINED 30 BILLION IMAGE AI MAP Niantic says photos and scans collected through Pokémon Go and its AR apps have produced a massive dataset of more than 30 billion real-world images. The company is now using that data to power visual navigation for delivery robots, letting them identify exact locations on city streets without relying on GPS. Source: NewsForce
English
763
3.5K
23.2K
22.2M
dustin
dustin@pyra_m1d·
@Newsforce probably one of the largest datasets ever created where the user paid to do the work themseleves. hilarious.
English
1
0
1
722
Tuki
Tuki@TukiFromKL·
The irony is brutal. The same corporate world that rejected neurodivergent people is now being replaced by AI. And the only people who can't be replaced... are the neurodivergent ones they rejected.
English
209
683
5K
580.1K
badbad 👺
badbad 👺@badbadwtf·
portal update we are starting to put the final touches on the new portal. this allow you to collect bread from NFTs, apparel purchases, IRL activations, content creation and more! this will be our biggest release to date and open up a whole new world to everyone that participates in our ecosystem. this will start rolling out end of April
English
3
2
5
129
badbad 👺
badbad 👺@badbadwtf·
we have been cooking so much we decided we need to bring back monthly spaces. moving forward these spaces will be every 3rd Thursday of the month. if you couldn't make it here's what you missed.
English
6
5
30
824
dustin
dustin@pyra_m1d·
Taylor is almost there but his metaphor is wrong. He calls it a "digital exoskeleton." It's not. It's a prosthetic. And the difference matters. An exoskeleton assumes you're whole. It assumes your business is whole. A prosthetic assumes something is missing — and restores it.
Dustin@r0ck3t23

Bret Taylor, former co-CEO of Salesforce and chair of OpenAI, just redefined the unit of productivity. It’s not a person. It’s a process. Taylor: “I think the atomic unit of productivity in AI is a process, not a person.” AI won’t replace a worker. It will compress entire workflows. What used to take 17 days across departments collapses into hours. The traditional corporate model measures productivity in person-hours. The new model measures process-compression. The incumbent assumption: you buy AI to replace a junior analyst. That’s a fundamental misunderstanding. You deploy an autonomous agent to completely collapse the timeline of a business outcome. An operation requiring 17 days of bureaucratic friction gets mathematically condensed into 17 hours. You’re not buying a digital employee. You’re buying the ruthless compression of time. Using AI to speed up a single employee’s task? You’re playing the wrong game. Taylor: “There’s a legal department to do a contract. There’s some finance department, procurement. You probably have IT that’s involved to onboard them into your core systems.” Friction in the modern enterprise doesn’t come from a single worker. It comes from the endless hand-offs between siloed departments. The traditional CEO tries making each department 10% faster. The winning CEO deploys an AI overlay that autonomously bypasses the human hand-offs entirely. The algorithm doesn’t sit in the legal department or IT. It executes the entire thread simultaneously across all core systems. It doesn’t replace individual workers. It renders their departmental bottlenecks completely irrelevant. Taylor: “I think it’s wrong to think about AI as sort of replacing people. In addition to being inhumane, it’s just sort of nonsensical because AI sort of operates in the world of digital technologies.” The neural network won’t sit at a desk, pour coffee, or shake a client’s hand. It’s a sovereign engine operating exclusively in the realm of digital friction. Superintelligence isn’t your direct replacement. It’s your digital exoskeleton. The hard part of enterprise execution has never been the human element. It’s always been wrestling with archaic, fragmented software systems. When AI takes over the digital process, the biological operator gets freed from the bureaucratic drag. They instantly shift from manual processor of forms to high-leverage director of outcomes. And that’s the real transformation. Not humans versus machines. Humans commanding the compressed timelines machines execute. Whoever builds that infrastructure first turns every competitor’s 17-day cycle into a fatal disadvantage. Because they’re finishing in hours what the rest of the market hasn’t even started.

English
1
0
2
73