RE: LeoThread 2025-07-02 07:22

“I hate the idea of having a Tesla-Kraken token and a Tesla-Robinhood token,” he said. “Instead of actually moving forward and creating a better financial system, we’re splitting [up] liquidity.”

Robinhood’s initiative highlights stark differences between major crypto trading platforms as they use tokenization to break from traditional methods of record keeping and create more efficient systems for investors.

In developing its own Ethereum-compatible network, based on Arbitrum’s design, Kerbrat said that Robinhood is trying to cast as large a net as possible, as it looks to expand on tokenized assets and connect with other entities within the cryptosphere.

“We’re launching [tokenized stocks and ETFs] first in the EU, but in the future, [we] want to open it up as soon as we get clarity on regulations,” he said. “We want the maximum participation there. We want to be compatible with other players.”

So, this leaves us with a few questions. What were the Big Beautiful Bill’s positions on AI? Why did the Senate overwhelmingly reject them? Can we expect the AI token market to continue showing reduced trade volumes and market capitalization?

The bill’s plan, essentially, was to impose a 10-year moratorium on AI regulation for all US states. This may have taken the form of an outright ban or a more roundabout method.

It would have proposed a $500 million fund on AI infrastructure development, but only states with zero AI regulations could access this money. Google and OpenAI supported this plan.

Such a vision would’ve created a lot of problems, and pro-crypto Senators even turned on it. If the bill banned AI regulation for 10 years, states would be powerless to prevent future AI-related crimes.

But crypto exchanges Kraken and Bybit have rolled out tokenized stock trading through Backed Finance’s xStocks. The assets, which trade on Solana, underscore how companies are leveraging competing networks and standards in trying to give the financial system a facelift.

As Kraken pushes forward with tokenized stock trading on Solana, Kerbrat noted that Ink, an Ethereum layer-2 network released by Kraken last year, has gone untapped.

“It’s interesting to see that they decided to not use that chain,” he said. “Some companies are about launching as many things as possible to get as many headlines as possible. On our side, we actually want people to use a product.”

A Kraken spokesperson told Decrypt that it joined the xStocks Alliance, a group of exchanges, networks, and decentralized finance protocols setting standards for on-chain assets, to avoid fragmenting liquidity across multiple token standards and chains.

Obvious offenses include fraud or copyright infringement, but people might even use AI tools to simulate depictions of child abuse, as some Senators warned. This possibility caused prominent Republicans like Marsha Blackburn to disavow the effort.

Unfortunately, it’s difficult to say how the bill will impact the AI token market in the long term. So far, the Big Beautiful Bill has been very unpredictable already.

For example, Elon Musk’s opposition to the bill caused several Musk-related meme coins to flourish, but Dogecoin fell by over 5%. This chaos could create new opportunities, but it’s uncertain where they’ll appear.

Additionally, the AI token sector was already in a slump before the bill passed. These 5% drops are concerning, but AI asset trade volumes fell over 38% in the last 30 days.

“We’re working to make xStocks the global standard for tokenized equities,” the spokesperson said. “This isn’t about promoting any single brand—it’s about unlocking access and shifting power back to the people.”

Solana was a natural place to launch xStocks to “accelerate mass adoption,” but Kraken is already working with a “broad network of partners” to expand xStocks to additional blockchains, the spokesperson said. Ink is a key part of the company’s roadmap, they added.

As Kraken leans into xStocks, Robinhood is preparing to debut its own Ethereum layer-2 scaling network, with the intent of appealing to as many developers as possible, too.

Grayscale logo on smart phone in dark room. Source: Shutterstock

In Cannes, Robinhood CEO Vlad Tenev said during an event on Monday that the firm is working with regulators to “bring the entire Robinhood ecosystem on-chain,” eventually leveraging its own blockchain for trading and settlement and supporting financial applications.

During a fireside with Ethereum co-founder Vitalik Buterin and Offchain Labs CSO A.J. Warner, Kerbrat later highlighted Arbitrum Stylus. As an engineer, he noted how difficult it can be to find “great engineers” that are adept in Ethereum’s programming language.

Arbitrum Stylus, which debuted in September, allows developers to write smart contracts in a variety of languages, including Rust, the primary language from programs on Solana.

“You can pull in specific libraries or specific components of your application using the Stylus stack and still take the benefits of the battle-hardened EVM code,” Warner said, noting that languages like c++ may appeal more to game developers or traditional finance firms.

Despite the technological milestone, Tesla shares fell about 1% in early trading Monday. The company's stock has declined more than 15% since the start of the year, as Tesla grapples with declining demand and increasing pressure from competitors.

The company has faced mounting challenges, particularly in key markets such as China and Europe, where such as China's BYD have taken the lead in the EV sector. Investors have also raised concerns about Tesla's aging vehicle lineup and its brand image, which has been affected by Musk's much-debated involvement with President Donald Trump and the Department of Government Efficiency.

The driverless delivery came shortly after Tesla initiated its Robotaxi program in Austin on a limited basis. While some influencers and analysts praised the program after participating in controlled test runs, others noted that the autonomous vehicles occasionally disobeyed local traffic laws.

The National Highway Traffic Safety Administration, which has previously scrutinized Tesla's self-driving efforts, confirmed it has requested more information about the Robotaxi pilot program.

Musk has long touted self-driving technology as a potential game-changer for Tesla's valuation, estimating that autonomous vehicles could add between $5 trillion and $10 trillion to the company's market cap by turning idle cars into active, income-generating assets.

Tesla is competing with other major players in the self-driving market, including Waymo, a company owned by Google. With this latest delivery, Tesla aims to demonstrate it can deliver real-world, fully autonomous performance, without a driver or remote assistance.

“They looked eerily similar to humans and are honestly very creepy,” one traveler said in a shared video. “This is freaky,” another said.

The guest’s discomfort reflects a trend in human-robot interaction, known as the “uncanny valley,” the eerie feeling that arises when machines look and behave almost like people, but not quite enough.

As UC Berkeley Industrial Engineering Professor Ken Goldberg once told Decrypt, “I want a robot to look like a robot—it can maybe do some things, but I don't want to confuse it with a real person.”

From Tokyo to Las Vegas, hotels are experimenting with machines to greet guests, answer questions, serve food, and trim labor costs.

In Japan, the Henn-na Hotel, also known as the “Strange Hotel,” has led the charge in adopting robotic staff. Opened in Nagasaki in 2015, it once boasted more than 240 robots and a minimal staff of humans.

Today, guests can still find humanoid androids behind check-in counters at the chain’s locations in Ginza, Hamamatsucho, Asakusabashi, Akasaka, and Haneda.

While the Henn-na Hotel drew headlines when it opened, problems soon emerged. By 2019, the hotel had retired more than half of its robotic staff due to technical glitches and guest complaints.

Based on traveler reviews, people love it—they describe interacting with the ‘staff’ as fun and rate the hotel overall highly," a spokesperson for Hotels.com told Decrypt. "The hotel has found a memorable way to add a little novelty and delight to the check-in experience, which seems to go over well with guests."

Despite mixed reactions, the rollout of robots in the hospitality industry is accelerating.

A recent report from Research and Markets projects the global hospitality robot market, including check-in, delivery, and cleaning bots, to grow from $648.2 million in 2024 to $2.2 billion by 2030, at a compound annual growth rate of 21.5%.

The surge is driven by post-COVID demand for contactless services, rising labor costs, and greater consumer acceptance of robotic staff.

Other major hotel chains that feature robot servers include Marriott, Hilton, IHG, Wyndham, Aloft, Crowne Plaza, and Renaissance, with robots delivering room service, amenities, and food to guest rooms.

In 2017, a 4-foot-tall robot named Pepper was introduced at the Mandarin Oriental Las Vegas as a “technical ambassador.”

After the hotel was sold and rebranded as the Waldorf Astoria Las Vegas, Pepper stuck around—greeting guests in the lobby, answering questions, and occasionally dancing.

“She was good,” a Waldorf Astoria representative told Decrypt. “She helped with lines at our front desk and entertained guests.” But Pepper was eventually retired, possibly after being damaged by visitors. “Someone got rough with it,” the employee said, noting that parts had gone missing.

However, it remains to be seen how much humans will accept robots taking over the travel industry and removing the “human touch” the industry has been known for.

While humanoid robots grab attention with their lifelike appearances, experts say the real transformation is more subtle.

Bitcoin’s role on company balance sheets is growing fast. According to a report, 199 entities now hold 3 million BTC, worth about $315 billion.

That total has more than doubled since the start of 2024. It marks a clear shift in how big firms view crypto, not just as a trading asset but as a long‑term treasury play.

Among those 199 entities, 147 public and private companies account for 1.1 million BTC (around $115 billion). Strategy, the pioneer in this space, holds 580,250 BTC—about $60 billion—and trades at a market cap of $104 billion.

That gives it a Multiple on Net Asset Value (MNAV) of 1.7× today. Investors once paid up to 2× NAV for Strategy’s shares, reflecting confidence in its ability to grow BTC‑per‑share faster than anyone else.

When a firm’s main business is holding Bitcoin, its shares need to outperform Bitcoin itself. That premium, known as MNAV, depends on faith in management and clear execution plans.

Strategy has used three main tools since 2020: issuing convertible debt, running an At‑the‑Market stock program, and plowing free cash flow into spot Bitcoin.

New rivals are copying and tweaking this playbook—letting holders swap coins for stock, buying underpriced firms to turn cash into BTC, and even adding private deals to raise funds.

“When people talk about humanoid robot receptionists, they usually picture the physical kind, like androids at the front desk,” Wyatt Mayham, CEO of Northwest AI Consulting, said. “But the real shift in hospitality AI is happening behind the scenes. Most hotels aren't betting on robots to check you in. They're putting their money into automation that actually solves day-to-day problems.”

As Mayham explained, behind-the-scenes investment reflects a deeper trend reshaping the hospitality industry from within.

An extended bear market could test these models. If Bitcoin falls and shares trade at or below NAV, debt‑heavy firms might struggle to refinance when notes come due.

That could force them to sell Bitcoin into a downtrend, pushing prices lower. Smaller companies without Strategy’s scale will face higher borrowing costs and tougher terms.

During a recession, margin calls and forced sales may cascade throughout the market, although most of these companies use equity financing mainly.

Stocks tied to the price of ether, better known as ETH, were higher on Wednesday, reflecting renewed enthusiasm for the crypto asset amid a surge of interest in stablecoins and tokenization.

BitMine Immersion Technologies, a bitcoin miner that announced plans this week to make ETH its primary treasury reserve asset, jumped about 20%. It's gained more than 1,000% since the announcement. Betting platform SharpLink Gaming, which has also initiated an ETH treasury strategy, added more than 11%. Bit Digital, which last week exited bitcoin mining to focus on its ETH treasury and staking plans, jumped more than 6%.

"We're finally at the point where real use cases are emerging, and stablecoins have been the first version of that at scale but they're going to open the door to a much bigger story around tokenizing other assets and using digital assets in new ways," Devin Ryan, head of financial technology research at Citizens.

On Tuesday, as bitcoin ETFs snapped a 15-day streak of inflows, ether ETFs saw $40 million in inflows led by BlackRock's iShares Ethereum Trust. ETH ETFs came back to life in June after much concern that they were becoming zombie funds.

The price of the coin itself was last higher by 5%, according to Coin Metrics, though it's still down 24% this year.

Governor Katie Hobbs issues a third veto on a pro-Bitcoin law in Arizona.
Bill HB 2324 proposed to create a state Bitcoin reserve from seized cryptos.
Hobbs cites volatility risks and the impact on local law enforcement.

Katie Hobbs stays on course. The Governor of Arizona has just issued a veto on bill HB 2324, which proposed establishing a Bitcoin reserve managed by the state.

This legislative initiative, adopted by 34 votes to 22 in the House of Representatives, would have allowed the creation of strategic reserves from cryptos confiscated during criminal investigations.

In her letter addressed to House Speaker Steve Montenegro, Hobbs justifies her decision with operational concerns.

She argues that this measure “disincentives local law enforcement from working with the state on digital asset forfeiture“. According to her, removing seized assets from local jurisdictions would harm inter-agency cooperation.

Ethereum has been struggling with an identity crisis fueled by uncertainty about the network's value proposition, weaker revenue since its last big technical upgrade and increasing competition from Solana. Market volatility, driven by geopolitical uncertainty this year, has not helped.

The Ethereum network's smart contracts capability makes it a prominent platform for the tokenization of traditional assets, which includes U.S. dollar-pegged stablecoins. Fundstrat's Tom Lee this week called Ethereum "the backbone and architecture" of stablecoins. Both Tether (USDT) and Circle's USD Coin (USDC) are issued on the network.

To that end, Robinhood has started quietly building its own blockchain, using Ethereum scaling tech to support 24/5 trading. It also launched tokenized shares of OpenAI and SpaceX — companies not publicly listed — to European users, marking a shift in how and where retail investors can gain exposure to top tech names.

"We thought we would just deliver," Tenev said. "We don't want to do much talking. We want to just put product in customers' hands."

Robinhood Crypto general manager Johann Kerbrat echoed that sentiment, saying the company is just getting started.

"In the future, we think we can expand this to thousands of tokens that represent different types of financial instruments — from U.S. stocks and international equities to private equity," he said. "What we showed today with SpaceX and OpenAI is just a glimpse of what we're planning — there's much more to come."

Robinhood's revenue rose 50% year-over-year in Q1, and the company just this week launched staking in the U.S. — a feature that had previously been blocked by regulators.

"To position Gaming for enduring success and allow us to focus on strategic growth areas, we will end or decrease work in certain areas of the business and follow Microsoft's lead in removing layers of management to increase agility and effectiveness," Phil Spencer, Microsoft's CEO of gaming, wrote in a Wednesday memo to employees in that division.

Microsoft reported nearly $26 billion in net income on $70 billion in revenue for the March quarter. The numbers were well ahead of Wall Street's consensus, keeping Microsoft ranked as one of the most profitable companies in the S&P 500 index, according to data compiled by FactSet.

Executives called for about 14% year-over-year revenue growth in the June quarter, thanks to expected expansion in Azure cloud services and corporate productivity software subscriptions

Microsoft stock closed at a record high of $497.45 per share on June 26. At the start of Wednesday's trading session, the shares were down about 0.6%, while the S&P 500 was roughly flat.

Autodesk, Chegg and CrowdStrike are among the other software providers that have slimmed down in 2025. Earlier on Wednesday, payroll processing company ADP said the U.S. private sector lost 33,000 jobs in June. Economists polled by Dow Jones had predicted an increase of 100,000.

Foldables represented less than 2% of the overall smartphone market in 2024, according to International Data Corporation. Samsung was the biggest player with 34% market share followed by Huawei with just under 24%, IDC added. Honor took the fourth spot with a nearly 11% share.

Honor is looking to get a head start on Samsung, which has its own foldable launch next week on July 9.

Francisco Jeronimo, a vice president at the International Data Corporation, said the Magic V5 is a strong offering from Honor.

"This is the dream foldable smartphone that any user who is interested in this category will think of," Jeronimo told CNBC, pointing to features such as the battery.

"This phone continues to push the bar forward, and it will challenge Samsung as they are about to launch their seventh generation of foldable phones," he added.

The thinness of a foldable phone has become a battleground for smartphone makers to appeal to consumers who want the large screen size the device has to offer without extra weight.

At its event next week, Samsung is expected to release a foldable that is thinner than its predecessor and could come close to challenging Honor's offering by way of size, analysts said. If that happens, then Honor will be facing more competition, especially against Samsung, which has a bigger global footprint.

"The biggest challenge for Honor is the brand equity and distribution reach vs Samsung, where the Korean vendor has the edge," Neil Shah, co-founder of Counterpoint Research, told CNBC.

Honor's push into international markets beyond China is still fairly young, with the company looking to build up its brand.

"Further, if Samsung catches up with a thinner form-factor in upcoming iterations, as it has been the real pioneer in foldables with its vertical integration expertise from displays to batteries, the differentiating factor might narrow for Honor," Shah added.

Since Trump's first term, Washington has been trying to onshore more of the advanced semiconductor supply chain from Asia, support its domestic players and limit China's capabilities.

Although tax provisions in Trump's sweeping policy bill expand on those in the Biden administration's CHIPS Act, his overall approach to the semiconductor industry has been different.

Earlier this year, the president even called for a repeal of the CHIPS Act, though Republican lawmakers have been reluctant to act on that front. Still, U.S. Commerce Secretary Howard Lutnick said last month that the administration was renegotiating some of the Biden administration's grants.

Trump has previously stated that tariffs, as opposed to the CHIPS Act grants, would be the best method of onshoring semiconductor production. The Trump administration is currently conducting an investigation into imports of semiconductor technology, which could result in new duties on the industry.

In recent months, a number of chipmakers with projects in the U.S. have ramped up planned investments there. That includes the world's largest contract chipmaker, TSMC, as well as American chip companies such as Nvidia, Micron and GlobalFoundries.

According to Daniel Newman, CEO at tech advisory firm Futurum Group, the threat of Trump's tariffs has created more urgency for semiconductor companies to expand U.S. capacity. If the increased investment tax credits come into law, those onshoring efforts are only expected to accelerate, he told CNBC.

"Given the risk of tariffs, increasing manufacturing in the U.S. remains a key consideration for these large semiconductor companies," Newman said, adding that the tax credits could be seen as an opportunity to offset certain costs related to U.S.-based projects.

XRP LEDGER EVM-SIDECHAIN MAINNET LAUNCHES: Ripple officially introduced the XRP Ledger's Ethereum Virtual Machine (EVM) sidechain to the mainnet in an bid to improve the ecosystem's interoperability and allow developers to deploy their Ethereum-based decentralized applications (dapps) with the XRPL. The development adds EVM-compatible smart contracts while maintaining a connection to the XRPL, giving developers access to the ecosystem at a low cost, Ripple said in a blog post. It is designed to eliminate the trade-off between EVM compatibility and XRPL’s own advantages, opening the door for dapps to lean into XRP’s payments infrastructure. The sidechain operates as a separate blockchain that is parallel and connected to the XRP Ledger over the Axelar bridge, an interoperability protocol. XRPL’s native token, XRP, will serve as the native gas token for the sidechain.

“Hotels are moving away from patchwork tools and toward integrated systems powered by AI,” he said. “The goal isn’t to replace people at the front desk, it’s to tighten operations and run leaner without losing service quality.”

For now, the robot receptionists are still employed at the Henn-na Hotel, but according to a recent report by travel website The Travel, the hotel’s staff is mostly human.

“We used a specialized AI program to analyze and match text fragments based on combinations of cuneiform signs,” Professor Enrique Jiménez, Professor of Ancient Oriental Languages at LMU, told Decrypt.

Jiménez and his colleagues use approaches based around natural language processing to indicate that fragments belong to a single text, as detailed in a methodology paper from last year.

Working from the Electronic Babylonian Library Platform, which contains 1,402 manuscripts, the researchers use n-gram matching as their primary method of reconstruction, although other methods include vocabulary overlapping and searching for longest common strings (of text).

According to Jiménez, the rediscovered poem was important enough to be taught as part of Babylon’s curriculum.

Los Angeles is Broke – City Declares Fiscal Emergency

The city of Los Angeles declared a state of fiscal emergency amid a $1 billion deficit. The council approved of the emergency declaration unanimously in a 14-0 vote. This comes after Mayor Karen Bass approved a $14 billion budget for the fiscal year that began on July 1. The city is a prime example of what happens when socialist policies are allowed to run rampant at the expense of the people.

Bass approved of raising the budget from $12.9 billion in FY2024-25 to $14 billion in 2025-26 despite the looming $1 billion deficit. Unsurprisingly, overspending is the main culprit for the deficit, and yet, lawmakers have every intention of spending more. Over 600 public sector workers will be let go as a result of fiscal mismanagement, and although small government is usually applaudable, the city plans to fire 248 LAPD employees, 44 sanitation workers, and 41 firefighters. LA is experiencing a significant uptick in crime, but plans to defund the police to appease the mobs.

California Governor Gavin Newsom boasts of California’s robust economy but fails to acknowledge that it’s a state basically living “paycheck-to-paycheck,” with the payee being the taxpayer. Read the state’s plan to cover its budget deficits – endless taxes. Spending growth from 2025-26 to 2028-29 is 5.8%, above the average of 3.5%. Growth over the same period is just above 4%, “lower than its historical average, largely due to policy choices that end during the forecast window. Taken together, we view it as unlikely that revenue growth will be fast enough to catch up to ongoing spending.” Even residents who choose or are forced to leave the state will incur taxes to cover government thievery. Los Angeles is one of countless examples of how the public sector will virtue signal to rob Peter, not to pay Paul, but to pay themselves, as they are not hiding the corruption.

Liability costs totaled $546 million in the past years, as there have been numerous lawsuits, mainly involving the Los Angeles Police Department, which is forbidden by law to enforce order. The city refused to budget for these growing legal battles. Not only does the city plan to fire officers, but they also reduced hiring by 50% last year, recruiting 240 new officers instead of the 480 needed to patrol the city.

I’ve reported numerous times how California uses the homeless epidemic to fund NGOs that merely steal from the taxpayers. Mayor Bass stated she plans to cut 10% of funding to the “Inside Safe” program. The city has spent millions on combating homelessness, and the numbers continue to rise.

Crime is more expensive than funding the LAPD. Criminals have cost the city of Los Angeles an estimated $7.6 billion annually. Gang violence alone costs the city around $1 billion per year, according to the Vera Institute of Justice, which is half of the annual budget of the LAPD. The California Department of Justice has acknowledged that property crime has risen in recent years and accounts for 60–70% of total losses. Yet, violent demonstrations are permitted to occur whenever Washington enacts a policy that displeases the Democrats.

Blue policies such as the net-zero climate initiative have caused businesses to flee Los Angeles and California as a whole. From 2020 to the present day, over 164 companies have left California. In the last year, 12 major companies like SpaceX, Chevron, X, and KFC have fled CA for TX. Los Angeles shed 106 corporate headquarters between 2018 and 2024, the second-highest number of losses in US metros behind San Francisco/San Jose.

Taxpayers are fleeing the state en masse. State and local taxes are among the highest in the nation and disproportionately harm the middle and upper classes to fund the growing public sector. Energy costs have skyrocketed, with major refiners abandoning California. Gas is expected to rise 75% by 2026, and residents are already paying the highest price for gas in the nation. The cost of living is exorbitant. Those who can have already fled as the government must continue to leech of the taxpayers to fund their failures.

There should be checks and balances against these elected officials who recklessly spend with no end in sight. Downsizing the police force is a political move that will only cause crime and the costs associated with crime to rise. Los Angeles is becoming a failed city as a direct result of socialist policies that have historically NEVER worked.

Robinhood is making its biggest bet on crypto yet, announcing on Monday that it’s developing an Ethereum layer-2 scaling network for trading digital representations of assets like stocks, while similar products exist already on competing networks like Solana.

For Johann Kerbrat, Robinhood's crypto general manager, the existence of multiple projects is frustrating. Tokenization becomes less beneficial when a digital version of the same stock is issued across multiple networks beneficial because activity is siloed across ecosystems, he told Decrypt.

Trump’s Big Beautiful Bill is a key piece of legislation that covers a huge range of topics. Intense political controversies caused the bill to change shape many times, but it finally passed the Senate today.

However, Senators overwhelmingly rejected the bill’s language supporting AI, showing a massive rebuke for the entire industry.

The vote was nearly unanimous, signaling real apprehension towards the industry. Indeed, the only Senator who voted for it, Thom Tillis, already announced that he won’t seek re-election.

A lot of cryptoassets are tied to the AI industry, and the market sector has taken some major hits since the bill’s language changed. Market cap and volume are both down over 5%:

Smiles, Trump at times does things that puts most people into confusion.

A Tesla Model Y SUV left the company's Gigafactory and drove itself about 30 minutes to a customer's house last Friday. The route included parking lots, highways, and city streets. Tesla shared a time-lapse video of the trip, emphasizing that the vehicle operated independently for the entire drive.

"There were no people in the car at all and no remote operators in control at any point. FULLY autonomous!" Musk posted on X.

Ashok Elluswamy, Tesla's head of AI, said the delivery was not staged.

We "literally chose a random customer who ordered a Model Y in the Austin area," he said. The car reportedly reached a top speed of 72 mph during the trip.

To be honest I love anything Tesla, but my problems is that the are freaking expensive. I don't think those cars are made for civil servants.

A TikTok video went viral on Monday, showing a woman laughing nervously as she backs away from a humanoid robot at Japan’s Henn-na Hotel.

“Don’t look at me,” she said, as the machine watched her. The scene underscores growing fears that robots are replacing humans in the workplace.

The awkward check-in has racked up hundreds of thousands of views and tapped into a deeper fear: robots that are a little too human.

This is a new era and robots have come to stay. My dear is that it will create a lot of unemployment.

Kind of creepy looking things, I'm with the folks that would rather have a regular looking bot.

Huh 🙄
Did you just arrive from space?
All the same, welcome back.
!LOLZ
!DOOK
!BBH

I think technology, overall, has always been a net positive for humanity. There are downsides to all of them.

Look at fire. A wonderful breakthough, most would agree, except when we set towns on fire.

Yeah Yeah Yeah. We know you like power. A domme all the way. LOL

Trying to fill it anyway I can. AI-summaries might be down for more than that unfortunately.

At an event held in a Belle Époque mansion along the French Riviera, Robinhood executives laid out a vision to bring thousands of tokenized stocks, ETFs, and private equities fully on-chain.

"This presentation and these products are dual-purpose," CEO Vlad Tenev told CNBC in Cannes. "The first purpose is obviously to deliver great products to users, but I think the second purpose is to just demonstrate very concretely how great it could be if crypto technology and traditional financial services could fully merge."

Microsoft has held several rounds of layoffs already this calendar year. In January, it cut less than 1% of headcount based on performance. The 50-year-old software company slashed more than 6,000 jobs in May and then at least 300 more in June. As of June 2024 it employed 228,000 people. In 2023, it laid off 10,000.

Perhaps the largest culling of Microsoft workers came in 2014, when the company eliminated 18,000 after acquiring Nokia's devices and services business.

As was the case with the May layoffs, Microsoft is looking to reduce the number of layers of managers that stand between individual contributors and top executives, said the person who asked not to be named while discussing internal matters.

Honor said the Magic V5 is 8.8 mm to 9mm when folded, depending on the color choice. The phone's predecessor, the Magic V3 — Honor skipped the Magic V4 name — was 9.2 mm when folded. Honor said the Magic V5 weighs 217 grams to 222 grams, again, depending on the color model. The previous version was 226 grams.

In China, Honor will launch a special 1 terabyte storage size version of the Magic V5, which it says will have a battery capacity of more than 6000 milliampere-hour — among the highest for foldable phones.

Honor has tried hard to tout these features, as competition in foldables ramps up, even as these types of devices have a very small share of the overall smartphone market.

Companies eligible for the credits could include chipmakers such as Intel, Taiwan Semiconductor Manufacturing Company and Micron Technology, provided that they expand their advanced manufacturing in the U.S. ahead of a 2026 deadline.

The new provisions expand on tax incentives under the 2022 CHIPS and Science Act, which provided grants of $39 billion and loans of $75 billion for U.S.-based semiconductor manufacturing projects.

But before the expanded credits come into play, Trump's sweeping domestic policy package will have to be passed again in the House, which narrowly passed its own version last month. The president has urged lawmakers to get the bill passed by July 4.

Researchers from LMU Munich and the University of Baghdad have used AI to reconstruct a Babylonian poem that had been lost for over 2,000 years.

Named the Hymn of Babylon, the text—which praises Babylon and the god Marduk—was written 3,000 years ago and last studied in 100 BC.

According to the team behind its rediscovery, it has been pieced together from 30 clay fragments that have been excavated over the years, with artificial intelligence being used to join the dots.

As the industry has gone mainstream with endorsements from major corporations and political figures, builders need to return to the ecosystem’s key ideals surrounding decentralization and building for users' needs, Buterin said.

In his typical jeans and relaxed dark T-shirt uniform, Buterin laid out practical “tests” that he said every crypto project should pass. These include 1) the walk-away test. If the company behind an application disappears, do users keep their assets? And 2) the insider attack test: How much damage can rogue insiders or compromised front-ends cause? And 3) whether it has a trusted computing base: How many lines of code must be trusted to protect users’ funds or data?

OpenAIStatus: OpenAI is a frontrunner, driven by its advancements in large language models like ChatGPT and subsequent models (e.g., o1, o3). CEO Sam Altman has claimed that humanity is already in the "era of superintelligence," with systems like ChatGPT outperforming humans in specific tasks and serving hundreds of millions daily. OpenAI's focus on recursive self-improvement—using AI to accelerate AI research—gives it a potential edge in scaling capabilities.

Strengths: Massive user base (over 200 million weekly ChatGPT users).
Strong partnership with Microsoft, providing vast computational resources.
Leadership in reasoning models and multimodal AI (text, voice, and more).

Challenges: Heavy reliance on Microsoft for infrastructure.
Faces competition from rivals catching up in model performance.
Internal concerns about alignment and safety as models grow more powerful.

Meta AI (Meta Superintelligence Labs)Status: Meta is aggressively positioning itself in the race, with CEO Mark Zuckerberg personally leading the formation of a "Superintelligence Labs" division. A $14.3 billion investment in Scale AI and the hiring of its CEO, Alexandr Wang, signal a major push. Meta has poached top talent from competitors like Google DeepMind, OpenAI, and Anthropic, offering compensation packages up to $100 million.

Strengths:Massive financial resources and a strategic 49% stake in Scale AI, providing access to vast AI training data.
Open-source approach with Llama models, fostering a broad developer community.
Extensive user base across Meta’s platforms (Facebook, Instagram, WhatsApp) for deploying AI solutions.

Challenges:Playing catch-up after Llama 4’s underwhelming performance and talent losses.
Internal skepticism, notably from Chief AI Scientist Yann LeCun, about the feasibility of achieving superintelligence via current large language model approaches.

Google (DeepMind and Gemini)Status: Google is a strong contender, leveraging decades of AI research through DeepMind and its Gemini models. Recent posts on X suggest Google has gained significant momentum, with some claiming it has surpassed OpenAI in public model performance.
Strengths:Unparalleled data access and infrastructure (e.g., TPUs, vast cloud resources).
Strong research output and a history of AI breakthroughs (e.g., AlphaGo).
Integration of AI across its product ecosystem (search, Android, etc.).

Challenges:Initially caught off-guard by ChatGPT’s success, requiring a pivot to catch up.
Gemini models are competitive but reportedly lag in developer adoption compared to OpenAI and Anthropic.

AnthropicStatus: Founded by ex-OpenAI researchers, Anthropic is a notable player with its Claude models (e.g., Claude 3.5 Sonnet), which rival OpenAI’s offerings in some benchmarks. It’s gaining traction as a counterweight to OpenAI and Microsoft.

Strengths:Backed by Amazon ($4 billion investment) and Alphabet, providing robust infrastructure.
Emphasis on safety and alignment, appealing to cautious enterprises.
Competitive models with strong performance in reasoning and multimodal tasks.

Challenges:Smaller user base compared to OpenAI and Meta.
Limited by a more conservative pace, though it’s accelerating.

xAIStatus: Led by Elon Musk, xAI is pushing for superintelligence with its Grok models and the Dojo supercomputer. Musk has predicted superhuman AI by 2026, and some X posts rank xAI as a top contender alongside Tesla’s AI efforts.

Strengths:Focused mission to accelerate human scientific discovery, potentially aligning with superintelligence goals.
Integration with Tesla’s AI capabilities (e.g., vision models, autonomous driving).
Musk’s willingness to take bold risks and invest heavily.

Challenges:Newer player with less established infrastructure compared to Google or Microsoft.
Chip and power supply constraints could hinder scaling.

Chinese AI Companies (e.g., DeepSeek, Qwen)Status: Chinese firms like DeepSeek and Qwen are emerging as significant players, with some X posts claiming they’ve achieved superintelligence or surpassed U.S. models in benchmarks. DeepSeek’s open-source model has disrupted the market by offering high performance at lower costs.

Strengths:Massive government backing and a national strategy prioritizing AI dominance by 2030.
Rapid progress in research output (e.g., surpassing the U.S. in AI patents) and talent development.
Cost-efficient models challenging U.S. dominance.

Challenges:Limited compute resources compared to U.S. counterparts.
Geopolitical tensions and export controls on advanced chips (e.g., Nvidia) may slow progress.

Who’s Winning?No single entity can be definitively declared the winner, as superintelligence remains an aspirational goal rather than a realized one. However, OpenAI holds a slight edge due to its early lead in generative AI, massive user adoption, and computational backing from Microsoft. Meta is a strong challenger, aggressively closing the gap with its talent acquisition and investment in Scale AI, though it faces internal and technical hurdles. Google is regaining momentum and could dominate if it leverages its data and infrastructure advantages effectively. Anthropic and xAI are wildcard contenders, with Anthropic excelling in safety-focused innovation and xAI benefiting from Musk’s ambitious vision. Chinese firms like DeepSeek are disruptive dark horses, potentially leading in cost efficiency but constrained by compute access.

Key ObservationsTalent Facets of the Race: The race is less about a single breakthrough and more about sustained investment in talent, compute power, and data. Meta’s aggressive spending (up to $65 billion in 2025) and OpenAI’s lead in model deployment highlight the financial intensity of the competition.

Talent War: Meta’s poaching of researchers from OpenAI, Google, and Anthropic underscores the critical role of human capital. The “Zuck Bucks” phenomenon—massive signing bonuses—reflects the high stakes.

Risks and Alignment: Concerns about AI alignment (ensuring AI goals align with human values) are growing, with OpenAI and Anthropic emphasizing safety but acknowledging challenges in defining “collective alignment” for superintelligent systems.

Global Dynamics: The U.S.-China AI race adds a geopolitical layer, with China’s rapid progress in patents and talent posing a long-term threat, though U.S. firms currently lead in compute and innovation.

ConclusionThe race for digital superintelligence is a tight contest among OpenAI, Meta, Google, Anthropic, xAI, and Chinese players like DeepSeek. OpenAI’s user base and model advancements give it a marginal lead, but Meta’s financial muscle and Google’s infrastructure could shift the balance. The outcome depends on breakthroughs in recursive self-improvement, compute scaling, and alignment solutions, with no clear timeline for superintelligence. The stakes are high, with potential to reshape economies and societies—or pose existential risks if misaligned.

LLaMA Series (Meta AI)Overview: Developed by Meta AI, the LLaMA series (LLaMA, LLaMA 2, LLaMA 3, LLaMA 3.1, LLaMA 4) is among the most influential open-source LLMs. LLaMA 3.1, released on July 23, 2024, includes models with 8B, 70B, and 405B parameters, with the 405B model being the largest open-source model to date. LLaMA 4, released in April 2025, introduced multimodal capabilities (text, images, short videos) and context windows up to 256,000 tokens.

Key Features:Optimized for research and enterprise applications, excelling in multilingual dialogue, reasoning, and coding.
LLaMA 3.1 405B supports complex tasks like synthetic data generation and knowledge distillation.
LLaMA 3.3 70B Instruct offers performance comparable to top closed-source models like GPT-4o, with a 128K-token context window.

License: Custom commercial license (free for users with under 700M monthly active users, with restrictions on using outputs to train other LLMs).

Use Cases: Enterprise AI (customer support, document summarization), scientific research (data analysis, literature reviews), and content creation (reports, technical documentation).

Relevance to Superintelligence: LLaMA’s open-weight models and massive parameter counts (405B in LLaMA 3.1) make it a cornerstone for research into scalable AI systems. Its multimodal capabilities and efficiency improvements position Meta as a leader in advancing toward AGI and potentially superintelligence.

Grok (xAI)Overview: Developed by xAI, founded by Elon Musk, Grok is integrated with the X platform and designed to provide real-time, transparent responses. It supports text generation, problem-solving, and code generation, with a focus on accelerating human scientific discovery.

Key Features:Native ability to generate search queries, cite sources, and trigger external tools via structured function calls.
Emphasizes transparency and reduced hallucinations, making it suitable for compliance-heavy industries.
Multimodal capabilities, including image generation from text prompts.

License: Not fully open-source, but xAI has released some model weights for research purposes under custom licenses. Specific licensing details for 2025 iterations are unclear.
Use Cases: Conversational AI, brainstorming, code generation, and real-time information retrieval for research and enterprise applications.

Relevance to Superintelligence: xAI’s mission to accelerate human discovery aligns with superintelligence goals. Grok’s integration with real-time data and focus on reasoning capabilities positions it as a contender for building systems that could approach AGI.

Gemma Series (Google DeepMind)Overview: Google’s Gemma models (Gemma 2, released June 2024) are lightweight, open-source LLMs with 9B and 27B parameters, built with technology similar to the proprietary Gemini models.

Key Features:Designed for text-only input/output, with an 8,000-token context window.
Can be run locally on personal computers or via Google Vertex AI.
Outperforms larger models like LLaMA 2 70B on key benchmarks despite smaller size.

License: Custom license with restrictions (models trained on Gemma outputs become derivatives subject to the same license).

Use Cases: Content generation, research, and lightweight deployment for businesses needing efficient NLP solutions.

Relevance to Superintelligence: While smaller than LLaMA or Grok, Gemma’s efficiency and performance make it a valuable platform for iterative research toward more advanced systems. Google’s broader AI ecosystem (e.g., Gemini) suggests Gemma is a stepping stone in their superintelligence roadmap.

OLMo-2-1B (Allen Institute for AI)Overview: Released in July 2025 by the Allen Institute, OLMo-2-1B is a compact, transparent model with 1B parameters, designed for research with fully open training data and logs.
Key Features:Emphasizes transparency, providing complete pre-training data, training code, and evaluation code.
Optimized for research into language model behavior and efficiency.

License: Fully open-source, likely under Apache 2.0 or similar permissive license.

Use Cases: Academic research, model analysis, and prototyping for NLP tasks.
Relevance to Superintelligence: OLMo’s focus on transparency makes it a critical tool for understanding LLM behavior, a key step in addressing alignment challenges for superintelligent systems. Its small size limits direct scalability but supports foundational research.

GPT-Neo, GPT-J, GPT-NeoX (EleutherAI)Overview: EleutherAI, a non-profit AI research group, has released several open-source LLMs, including GPT-Neo, GPT-J, and GPT-NeoX-20B (20B parameters). These models aim to replicate GPT-3’s capabilities and were trained on The Pile, an 825GB diverse dataset.

Key Features:GPT-NeoX-20B is the largest, designed for few-shot learning and research, with performance rivaling larger proprietary models.
Autoregressive architecture similar to GPT-3, optimized for content generation and NLP tasks.

License: Apache 2.0, allowing commercial use and modifications.

Use Cases: Content generation (marketing, media), research, and prototyping for NLP applications like text classification and question answering.

Relevance to Superintelligence: EleutherAI’s models provide accessible platforms for researchers to experiment with large-scale architectures, contributing to collective efforts toward AGI. Their open nature fosters community-driven advancements critical for superintelligence research.

Pythia (EleutherAI)Overview: Pythia is a series of 16 LLMs (up to 12B parameters) released by EleutherAI, designed for analyzing LLM training and scaling dynamics.

Key Features:Focused on research, with transparent training processes and datasets.
Supports tasks like text generation, summarization, and reasoning.

License: Apache 2.0, fully open for commercial and research use.

Use Cases: Academic research, model scaling studies, and benchmarking NLP tasks.
Relevance to Superintelligence: Pythia’s emphasis on understanding scaling laws and training dynamics is crucial for designing more efficient, larger models that could approach superintelligence.

BLOOM (BigScience, coordinated by Hugging Face)Overview: BLOOM, released in July 2022, is a 176B-parameter multilingual LLM developed by over 1,000 researchers, coordinated by Hugging Face (U.S.-based). It supports 46 languages and 13 programming languages.

Key Features:Decoder-only transformer, excels in text generation, summarization, and translation.
Trained on a diverse dataset, making it ideal for global applications.

License: OpenRAIL-M, allowing commercial use with ethical constraints.

Use Cases: Multilingual content generation, translation, and research for global businesses.

Relevance to Superintelligence: BLOOM’s scale and multilingual capabilities make it a testbed for large-scale AI systems, though its computational demands limit widespread adoption. Its collaborative development model supports community-driven progress toward advanced AI.

Granite Series (IBM)Overview: IBM’s Granite models, with releases in May, October, and December 2024 (Granite 3.1), are fully open-source LLMs with 8B and 2B variants, optimized for enterprise use.

Key Features:General-purpose, guardrail, and Mixture-of-Experts models for tasks like customer service, IT automation, and cybersecurity.
Trained on diverse datasets, with a focus on enterprise reliability.

License: Apache 2.0, fully open for commercial use.

Use Cases: Enterprise applications (customer support, cybersecurity), data analysis, and compliance-heavy industries.

Relevance to Superintelligence: Granite’s enterprise focus and open-source nature make it a practical platform for scaling AI in controlled environments, contributing to robust, aligned systems.

Phi-3 Mini (Microsoft)Overview: Released in 2024, Phi-3 Mini is a 3.8B-parameter LLM designed for efficiency, running on low-cost hardware like T4 GPUs.

Key Features:Achieves performance rivaling larger 7B/8B models, with a 128K-token context window variant.
Optimized for English-only tasks like chat and code completion.

License: MIT, highly permissive for unrestricted commercial use.

Use Cases: Low-cost inference for small businesses, chatbots, and code generation.

Relevance to Superintelligence: Phi-3’s efficiency makes it a candidate for edge-based AI, potentially integrating into larger systems for distributed superintelligence applications.

DBRX (Databricks, MosaicML)Overview: DBRX, developed by Databricks and MosaicML, is a Mixture-of-Experts model with 36B active parameters (132B total), released in 2024.

Key Features:Uses 16 experts, selecting 4 per inference, offering 65x more expert combinations than similar models.
Excels in retrieval-augmented generation and code-related tasks.

License: Custom open-source license for commercial use.

Use Cases: Enterprise AI, code generation, and data-intensive applications.

Relevance to Superintelligence: DBRX’s efficient MoE architecture is a step toward scalable, compute-efficient systems critical for superintelligence.

The U.S. is a hub for open-source LLMs, with Meta’s LLaMA series leading due to its scale and multimodal capabilities, followed by xAI’s Grok for real-time applications, and Google’s Gemma for lightweight efficiency. EleutherAI, Allen Institute, IBM, Microsoft, and Databricks contribute diverse, accessible models that fuel research and enterprise applications. These LLMs are critical to the superintelligence race by enabling global collaboration, transparency, and experimentation, though computational and alignment challenges remain. For the latest updates, you can explore platforms like Hugging Face or follow X posts from AI researchers

Challenges and ConsiderationsComputational Demands: Models like LLaMA 3.1 405B and BLOOM require significant GPU resources, limiting accessibility for smaller organizations.

Alignment and Safety: Open-source models like Zephyr-7B-alpha (not listed above but mentioned in sources) lack RLHF, risking problematic outputs, which is a critical concern for superintelligence development.

Licensing Restrictions: While Apache 2.0 (Granite, Pythia) and MIT (Phi-3) licenses are permissive, LLaMA and Gemma’s custom licenses impose restrictions, potentially slowing community-driven progress.

Global Competition: U.S. open-source LLMs face competition from international models like DeepSeek-V3 (China) and Mistral (France), which offer comparable performance with fewer restrictions.

Meta AI (LLaMA): Meta’s aggressive push with LLaMA 3.1 and LLaMA 4, backed by a $65 billion investment in 2025 and talent acquisition from Scale AI, positions it as a leader. Its open-weight models enable global research, accelerating innovation toward AGI, though its custom license limits some commercial applications.

xAI (Grok): xAI’s focus on real-time data integration and reasoning aligns with superintelligence goals, but its less open licensing may restrict community contributions compared to LLaMA or Granite.
Google (Gemma): Gemma’s lightweight design complements Google’s proprietary Gemini models, suggesting a dual strategy of open-source research and closed-source scaling toward superintelligence.

Smaller Players (EleutherAI, Allen Institute, Hugging Face): These organizations foster transparency and community-driven development, crucial for addressing alignment and safety challenges in superintelligence. Their models, while smaller, provide foundational insights for scaling.
IBM and Microsoft: Granite and Phi-3 focus on enterprise and edge efficiency, respectively, contributing to practical, scalable AI systems that could integrate into larger superintelligent frameworks.
Databricks (DBRX): Its MoE architecture offers a compute-efficient path to scaling, a key consideration for superintelligence development.