@Crypto_Dep: @RobinhoodApp unveils a suite of new products, including US stock trading and its own L2 Robinhood unveils stock tokens, expands crypto offerings in the EU and US with perpetual futures & staking, and introduces its own L2 blockchain. Stock tokens will be initially launched on @ArbitrumARB 0.00%↑ , then move to Robinhood’s Arbitrum-based Layer 2 blockchain.
phind.com (Phind-70B): [Sources not verified. Do your own research] Microsoft+OpenAI’s Key Areas of Tension.
Discount Strategy Conflict - OpenAI has begun offering enterprise clients discounts ranging from 10% to 20% on ChatGPT subscriptions.
These discounts come with requirements to purchase other OpenAI products.
Microsoft is reportedly unhappy with this pricing strategy, as they typically maintain consistent enterprise pricing without deep discounts.
This has led to Microsoft losing some deals due to inability to match OpenAI's discounted rates.
Contract Modification Demands - OpenAI wants to revise several key terms in its contract with Microsoft.
Specifically seeks to modify clauses giving Microsoft exclusive rights to host OpenAI models.
Proposing Microsoft hold a 33% stake in a restructured unit.
Wants to reduce Microsoft's control over its AI products and computing resources.
Anticompetitive Concerns - OpenAI executives are considering accusing Microsoft of anticompetitive behavior.
They might seek federal regulatory review of their contract.
Potential violations of antitrust law could be investigated.
This represents a significant escalation in their business relationship tensions.
Mermaid diagram:
Dotted lines indicate points of conflict or opposition.
Blue nodes represent OpenAI initiatives.
Red nodes represent Microsoft positions.
Orange nodes highlight areas of tension.
Flowchart that illustrates: 1. Current partnership structure 2. Points of conflict 3. Future implications. Solid arrows show direct actions and relationships
+ Related content:
ft.com (update; 6/19/25): [Excerpt] Microsoft prepared to walk away from high-stakes OpenAI talks. ChatGPT maker’s plans to convert into a for-profit leads software giant to make contingency plans.
In discussions over the past year, the two sides have battled over how much equity in the restructured group Microsoft should receive in exchange for the more than $13bn it has invested in OpenAI to date. Discussions over the stake have ranged from 20 per cent to 49 per cent. The pair are also revising the terms of its wider contract, first drafted when Microsoft invested $1bn into OpenAI in 2019.
Under its current arrangement, Microsoft has exclusive rights to sell access to OpenAI’s models and receives a 20 per cent share of revenues up to $92bn.
🙂
☑️ #202 Jun 16, 2025
OpenAI wins $200 million U.S. defense contract
openai.com: [Excerpt] Introducing OpenAI for Government.
We are proud to share that our first partnership under this new OpenAI for Government initiative will be a pilot program with the U.S. Department of Defense through their Chief Digital and Artificial Intelligence Office (CDAO). This contract, with a $200 million ceiling, will bring OpenAI’s industry-leading expertise to help the Defense Department identify and prototype how frontier AI can transform its administrative operations, from improving how service members and their families get health care, to streamlining how they look at program and acquisition data, to supporting proactive cyber defense. All use cases must be consistent with OpenAI's usage policies and guidelines.
Across these efforts, we’re aiming to improve both the day-to-day experience of public service and to help government employees feel more empowered, more efficient, and more supported in their critical missions. We are already seeing how OpenAI can help public servants at the state level spend less time on repetitive tasks and more time on high-impact work. For example, Commonwealth of Pennsylvania employees participating in an OpenAI pilot program(opens in a new window) found ChatGPT helped reduce the time spent on routine tasks by about 105 minutes per day. And, at the federal level, we’re already seeing how it can improve the quality of services delivered. At Los Alamos, Lawrence Livermore, and Sandia National Labs we are deploying OpenAI models to accelerate scientific research, bolster national security readiness, and drive public sector innovation.
linkedin.com > Felipe Millon: 🇺🇸 I'm incredibly proud to share that OpenAI has been awarded a $200 million contract with the U.S. Department of Defense through their Chief Digital and Artificial Intelligence Office (CDAO). This collaboration is a testament to the innovative spirit and forward-thinking approach of the DOD in harnessing technology to better serve our nation.
We also announced that we are organizing all of our public sector work under a new initiative: OpenAI for Government. We're seeing remarkable momentum in the U.S. government's adoption of AI, from reducing red tape and administrative burdens to bolstering national security readiness. At OpenAI, we're deeply committed to partnering with agencies across federal, state, and local governments to deliver AI solutions that make a tangible difference. Exciting times ahead—stay tuned! https://www.cnbc.com/2025/06/16/openai-wins-200-million-us-defense-contract.html
🙂
☑️ #202 Jun 11, 2025 🔴 rumor
Exclusive: OpenAI taps Google in unprecedented cloud deal despite AI rivalry, sources say
reuters.com: [Excerpt] SAN FRANCISCO, June 10 (Reuters) - OpenAI plans to add Alphabet's (GOOGL.O), opens new tab Google cloud service to meet its growing needs for computing capacity, three sources told Reuters, marking a surprising collaboration between two prominent competitors in the artificial intelligence sector.
The deal, which has been under discussion for a few months, was finalized in May, one of the sources added. It underscores how massive computing demands to train and deploy AI models are reshaping the competitive dynamics in AI, and marks OpenAI's latest move to diversify its compute sources beyond its major supporter Microsoft (MSFT.O), opens new tab, including its high-profile Stargate data center project.
Deal reshapes AI competitive dynamics, Google expands compute availability.
OpenAI reduces dependency on Microsoft by turning to Google.
Google faces pressure to balance its external cloud offering and AI development.
Oracle to buy $40bn of Nvidia chips for OpenAI’s new US data centre
ft.com: [Excerpt] Chips will be used in OpenAl's new data center in Abilene. The site's owners, Crusoe and the US investment firm Blue Owl Capital, have raised $15 billion in debt and equity to finance the Abilene project.
+ Related content:
crusoe.ai (5/21/25): [Excerpt] Crusoe, Blue Owl Capital, And Primary Digital Infrastructure Enter Second Phase Of $15 Billion Joint Venture To Fund AI Data Center In Abilene, Texas.
Under the terms of the joint venture, Crusoe in combination with funds managed by Blue Owl’s Real Assets platform along with Primary Digital Infrastructure will jointly sponsor the construction of six new buildings, which will bring the center to eight buildings upon completion. Construction of the first phase, comprising two buildings and 200+ megawatts, began in June 2024 and is expected to be energized in the first half of 2025. Construction of the second phase, consisting of the six additional buildings and a total of 1.2 gigawatts, began in March 2025 and is expected to be energized in mid-2026, setting a new bar for the speed of delivery for green-field, hyperscale digital infrastructure projects.
Source: Crusoe Energy Systems, LLC
crusoe.ai (3/18/25): [Excerpt] Crusoe Expands AI Data Center Campus In Abilene To 1.2 Gigawatts.
SAN FRANCISCO, CA / ABILENE, TX / March 18, 2025 / - Today Crusoe, the industry’s first vertically integrated AI infrastructure provider, announced construction has begun on the next phase of its AI data center at the Lancium Clean Campus in Abilene, Texas. The second phase of construction, expected to be completed in mid-2026, includes six additional buildings, bringing the total facility to eight buildings, approximately 4 million square feet, and a total power capacity of 1.2 gigawatts (GW). With this announcement, Crusoe's total data center footprint will reach more than 1.6 GW under operations and construction with an additional pipeline exceeding 10 GW in development.
Crusoe began constructing the AI data center in Abilene in June 2024. The initial phase, comprising two buildings at 980,000 square feet and 200+ megawatts, is expected to be energized in the first half of 2025. Designed and built by Crusoe at the Lancium Clean Campus, the project incorporates innovative data center design to support powerful AI workloads. Each building is designed to operate up to 50,000 NVIDIA GB200 NVL72s on a single integrated network fabric, advancing the frontier of data center design and scale for AI training and inference workloads. The construction site has approximately 2,000 people working on the project daily and is expected to reach nearly 5,000 as a result of the expansion. The Development Corporation of Abilene (DCOA) has previously estimated that the direct and indirect economic impact of the initial phase of the project is approximately $1 billion over 20 years. This expansion has the potential to scale that impact by many magnitudes.
blueowl.com (5/15/25): [Excerpt] Blue Owl Capital Announces $7 Billion Final Close for Digital Infrastructure Fund.
Blue Owl Digital Infrastructure Fund III seeks to support the global capital demands of hyperscalers, fueled by ongoing investments in data centers and artificial intelligence.
NEW YORK, New York, May 15, 2025 -- Blue Owl Capital Inc. ("Blue Owl") (NYSE: OWL), a leading alternative asset manager, announced today the final close of its most recent digital infrastructure fund, Blue Owl Digital Infrastructure Fund III ("ODI III") with $7 billion of total capital commitments. ODI III exceeded the original target of $4 billion and hit its hard cap.
ODI III will focus on developing, acquiring, and owning data centers and other connectivity related real assets to help meet the AI and cloud-driven global digital capacity needs of the world's largest technology companies, with a focus on large-scale, build-to-suit developments.
The funding will be a mixture of debt and equity and includes contributions from Crusoe and Blue Owl Capital.
🙂
☑️ #200 May 21, 2025
Sam & Jony introduce io
@OpenAI: Building a family of AI products for everyone.
Computers are now seeing, thinking and understanding.
Source: OpenAI, L.L.C.
@BenGeskin (5/22/25): WSJ on Jony Ive and Sam Altman’s OpenAI device:
The product will be capable of being fully aware of a user's surroundings and life, will be unobtrusive, able to rest in one's pocket or on one's desk, and will be a third core device a person would put on a desk after a MacBook Pro and an iPhone.
The Journal earlier reported that the device won't be a phone, and that Ive and Altman's intent is to help wean users from screens.
Altman said that the device isn't a pair of glasses, and that Ive had been skeptical about building something to wear on the body.
wsj.com: [Excerpt] What Sam Altman Told OpenAI About the Secret Device He’s Making With Jony Ive. Idea is a ‘chance to do the biggest thing we’ve ever done as a company here,’ Altman told OpenAI employees Wednesday.
Altman and Ive also offered details about how their collaboration grew in the last several years. Eighteen months ago, OpenAI’s Vice President of Product Peter Welinder began working with Ive’s team. The two sides became excited about a specific device last fall.
The original plan was for Ive’s startup to build and sell its own device using OpenAI’s technology, but Altman said he eventually realized that wouldn’t work. Altman said he knew the two companies would have to be combined because the device wasn’t just an accessory but a central facet of the user relationship with OpenAI.
bloomberg.com: [Excerpt] Jony Ive and OpenAI Make a Long-Shot Bet to Kill the iPhone. It will be vastly more difficult for the new partnership to create a killer AI device than it will be for Apple to create an AI offering good enough to maintain the iPhone’s supremacy.
Speaking to Bloomberg News, Altman suggested he didn’t think the device would replace a smartphone, at least not at first. So, OpenAI will need first to convince users to incorporate an extra gadget into their day. Those consumers will need to be convinced it brings functionality far superior to what they can summon with the smartphone already in their pocket. If OpenAI eventually decides it wants to make a product to replace the smartphone or laptop — those “legacy” devices, as Ive put it — it will need to work out how to break iOS users from lock-in, or Windows users from the tools they need every day for work.
If it’s confident it can do all that, OpenAI then needs to figure out how to manufacture it. Apple has 695 suppliers, according to Bloomberg data, coexisting in a delicate dance that means the iPhone arrives in consumers’ hands at a price they can stomach. OpenAI has no such network — nor the institutional knowledge (yet) to create one.
Confirmed by OpenAI
OpenAl will be taking over former Apple Design Chief Jony Ive's hardware start-up io Products, in a deal worth $6.5 billion. Ive will be taking on design and creative responsibilities across OpenAl and io.
🙂
☑️ #199 May 20, 2025
Inside OpenAI's Stargate Megafactory with Sam Altman | The Circuit
@business: Emily Chang visits the Stargate site in Abilene, Texas for an exclusive first look at the historic $500 billion bet on the future of AI, announced by President Trump the day after his inauguration. She speaks with OpenAI CEO Sam Altman & Softbank CEO Masayoshi Son about why they have partnered, along with Oracle, to build one of the largest AI data centers in the world. Watch more episodes of The Circuit with Emily Chang:
@OpenAI: Every idea, every breakthrough, every leap forward—begins with a single starting point. What will you create next?
🙂
☑️ #196 Feb 3, 2025
Cristal Intelligence
group.softbank: [Excerpt] OpenAI and SoftBank Group Partner to Develop and Market Advanced Enterprise AI.
A Vision to Transform Industry with Cristal intelligence
In 2024, OpenAI launched their o1-series, AI models capable of reasoning. In 2025, these models will evolve into agents, AIs capable of doing work for you independently – you give it a task and it will execute it.
AI agents for knowledge work will automate everyday tasks – such as generating financial reports, drafting documents, and managing customer inquiries – to empower professionals to focus on creativity and strategic decision-making.
OpenAI, SoftBank Group Corp., Arm and SoftBank Corp. share a vision to enable AI agents to help make every knowledge worker more effective and solve even more complex problems. With Cristal intelligence, these AI agents will lay the groundwork for even more advanced systems that can learn and adapt to any enterprise’s needs.
ft.com: [Excerpt] Deal would make Japanese group biggest financial backer in ChatGPT maker.
The deal, which has not been finalised, is an ambitious gambit by SoftBank founder Masayoshi Son to become a leading force in AI by deepening ties with OpenAI and its chief executive Sam Altman.
An investment of $15bn or more would make the Japanese investor OpenAI’s largest single backer. Microsoft — which first invested in OpenAI in 2019 — is the start-up’s biggest shareholder.
OpenAI pledges to work with Washington to stop rivals unfairly copying its technology
@FoxNews: 'We have to be the leader in AI,' White House AI and crypto 'czar' says.
Tech titan David Sacks reveals the status of the country's tech race with China and why U.S. data centers are important on 'The Story.'
+ Related content:
ft.com: [Excerpt] OpenAI says it has evidence China’s DeepSeek used its model to train competitor. White House AI tsar David Sacks raises possibility of alleged intellectual property theft.
The San Francisco-based ChatGPT maker told the Financial Times it had seen some evidence of “distillation”, which it suspects to be from DeepSeek.
The technique is used by developers to obtain better performance on smaller models by using outputs from larger, more capable ones, allowing them to achieve similar results on specific tasks at a much lower cost.
Distillation is a common practice in the industry but the concern was that DeepSeek may be doing it to build its own rival model, which is a breach of OpenAI’s terms of service.
bloomberg.com: [Excerpt] Microsoft Probing If DeepSeek-Linked Group Improperly Obtained OpenAI Data.
Microsoft’s security researchers in the fall observed individuals they believe may be linked to DeepSeek exfiltrating a large amount of data using the OpenAI application programming interface, or API, said the people, who asked not to be identified because the matter is confidential. Software developers can pay for a license to use the API to integrate OpenAI’s proprietary artificial intelligence models into their own applications.
openai.com (1/28/25): [Excerpt] Introducing ChatGPT Gov. ChatGPT Gov is designed to streamline government agencies’ access to OpenAI’s frontier models.
Agencies can deploy ChatGPT Gov in their own Microsoft Azure commercial cloud or Azure Government cloud on top of Microsoft’s Azure’s OpenAI (opens in a new window)Service. Self-hosting ChatGPT Gov enables agencies to more easily manage their own security, privacy, and compliance requirements, such as stringent cybersecurity frameworks (IL5, CJIS, ITAR, FedRAMP High). Additionally, we believe this infrastructure will expedite internal authorization of OpenAI’s tools for the handling of non-public sensitive data. Use of ChatGPT Gov is subject to our usage policies, like other OpenAI services.
chatgpt.com (ChatGPT 4o mini): [Sources not verified. Do your own research] It does sound like DeepSeek, especially with its R1 model, could be positioning itself as a major competitor to OpenAI's models like GPT-3 (o3) or GPT-4 (o4), especially if it's outperforming those models in terms of cost-efficiency and coding benchmarks. The claim that it's 25x cheaper and potentially outperforms OpenAI’s offerings at the same price point is definitely eye-catching, and if the chain-of-thought reasoning leads to high-quality, consistent outputs, it would be a significant advantage.
As for whether OpenAI’s investors are worried—it's hard to say for sure without insider knowledge, but they’d definitely have reason to take notice. The AI space is extremely competitive, and any major leap in performance at a dramatically lower cost could quickly change the game. OpenAI has historically been at the forefront of innovation, but there are always risks of newer players emerging with better solutions that shake up the landscape.
If DeepSeek-R1 really lives up to these claims, and given the accelerating pace of AI advancements, OpenAI would likely be keeping a very close eye on this development. But whether they’re actively worried or just analyzing it as part of normal competitive dynamics—who knows? They might see it as a prompt to further innovate, or they could have strategic plans already in place to counter any emerging threats.
It’s definitely an interesting space to watch. What do you think? Do you see DeepSeek as a true game-changer, or do you think it’s too early to make that call?
+ Related content:
@sama: deepseek's r1 is an impressive model, particularly around what they're able to deliver for the price. we will obviously deliver much better models and also it's legit invigorating to have a new competitor! we will pull up some releases.
[2] but mostly we are excited to continue to execute on our research roadmap and believe more compute is more important now than ever before to succeed at our mission. the world is going to want to use a LOT of ai, and really be quite amazed by the next gen models coming.
[3] look forward to bringing you all AGI and beyond.
🙂
☑️ #192 Jan 21, 2025
Announcing The Stargate Project
openai.com: [Excerpt] Arm, Microsoft, NVIDIA, Oracle, and OpenAI are the key initial technology partners. The buildout is currently underway, starting in Texas, and we are evaluating potential sites across the country for more campuses as we finalize definitive agreements.
OpenAI, and our strategic partners, are thrilled about our shared vision for new AI infrastructure in the United States. We are energized by the challenges we face and are excited by the prospect of partnering with firms across the industrial base to deliver against our ambitious mission. Specifically, we want to connect with firms across the built data center infrastructure landscape, from power and land to construction to equipment, and everything in between.
[Topic] DeepSeek R1 100% “Open Source” and 95% cheaper than OpenAI o1?
perplexity.ai (DeepSeek R1): [Sources not verified. Do your own research] DeepSeek's open-source initiatives, such as DeepSeek-Coder and DeepSeek-V2/DeepSeek-V3, have contributed significantly to the AI community, but the specifics of their "R1" model and claims about being 100% open source, 95% cheaper than OpenAI, and delivering similar performance require careful scrutiny:
Is DeepSeek R1 100% Open Source?
Open-Source Definition: For a model to be "100% open source," its weights, training code, data recipes, and inference frameworks must be publicly released under a permissive license (e.g., Apache 2.0, MIT).
DeepSeek's Track Record:
Models like DeepSeek-Coder-33B and DeepSeek-V2 have partially open-sourced weights (e.g., base models but not fine-tuned versions) and limited documentation on training data/methods.
The most advanced optimizations (e.g., MoE architectures, quantization) are often kept proprietary.
R1 Status: If "R1" follows this pattern, it may release weights under a restrictive license (e.g., non-commercial use only) or omit critical components (training code, data). Verify the license on platforms like Hugging Face or GitHub.
Cost Comparison: 95% Cheaper Than OpenAI?
OpenAI Costs: GPT-4 Turbo costs ~$0.01/1k input tokens and $0.03/1k output tokens. For large-scale usage, this adds up quickly.
DeepSeek R1 Cost Claims:
If self-hosted, costs depend on hardware (e.g., running a 30B parameter model on A100 GPUs vs. quantized on consumer GPUs). Self-hosting can be cheaper long-term but requires upfront infrastructure investment.
If offered via an API, DeepSeek would need to undercut OpenAI significantly (e.g., $0.0005/1k tokens). No public pricing for "R1" exists yet; verify their official docs.
Savings Context: A 95% reduction is plausible for self-hosted models (avoiding API markup), but not guaranteed for all use cases.
Performance Comparison
Benchmarks:
DeepSeek-Coder-33B rivals GPT-4 in coding tasks (e.g., HumanEval).
General-purpose models like DeepSeek-V2 claim GPT-4-level performance in Chinese benchmarks but lag in broader multilingual tasks.
R1's Performance: If "R1" is a specialized model (e.g., coding, math), it may match OpenAI in niche areas. For general use, performance gaps likely exist.
Key Considerations:
Transparency: Even "open-source" models often lack full training data/methods, limiting reproducibility.
Total Cost of Ownership: Self-hosting savings depend on scale, hardware, and engineering effort.
Licensing: Check if "R1" permits commercial use or imposes restrictions (e.g., non-compete clauses).
Conclusion:
100% Open Source? Unlikely—expect partial openness (weights only, restrictive license).
95% Cheaper? Possible for self-hosted scenarios, but not universally applicable.
Similar Performance? Task-dependent; competitive in niches (coding), less so in general use.
Always verify claims against official documentation and independent benchmarks.
What are the main differences in the training methodologies between DeepSeek R1 and OpenAI o1. Source: Perplexity.ai
🙂
☑️ #190 Jan 15, 2025
OpenAI to fund four new Axios Local newsrooms
axios.com: [Excerpt] Zoom in: As part of the three-year deal, OpenAI will fund Axios' expansion into Pittsburgh; Kansas City, Missouri; Boulder, Colorado; and Huntsville, Alabama, the companies said.
ChatGPT will use Axios journalism to answer user queries with attributed summaries, quotes and links to Axios stories. Axios can access OpenAI's technology to build its own AI products, processes, and systems.
[Topic] Marc Toberoff representing Elon Musk in a high-profile legal battle against OpenAI
@grok: [Sources not verified. Do your own research] The legal battle between Elon Musk and OpenAI, where Marc Toberoff is representing Musk, has seen several escalations, primarily revolving around Musk's allegations that OpenAI has deviated from its original mission. Here are the key objectives of this judicial strategy based on recent developments:
Enforcement of Original Mission:
Objective: Musk's lawsuit aims to enforce what he claims was the original agreement or mission of OpenAI to develop artificial intelligence for the benefit of humanity, not for profit. Musk alleges that OpenAI has breached this founding agreement by shifting towards a for-profit model, particularly after its partnership with Microsoft intensified.
Blocking Conversion to For-Profit:
Objective: One of the central demands in the lawsuit is to block OpenAI from converting into a fully for-profit entity. Musk has sought a preliminary injunction to prevent this transition, arguing that such a change would be detrimental to the original nonprofit ethos of OpenAI.
Antitrust Claims and Market Control:
Objective: Musk's legal team has expanded the complaint to include federal antitrust allegations, claiming that OpenAI, in collaboration with Microsoft, attempted to monopolize the AI market, particularly by allegedly discouraging investors from funding competitors like Musk's xAI. This part of the strategy seeks to address what Musk sees as anticompetitive practices.
Restoration of Nonprofit Status and Public Benefit:
Objective: Musk seeks to restore OpenAI's operations to align with its nonprofit status, including making its research and technology publicly accessible. He wants judicial rulings to compel OpenAI to maintain its focus on public benefit rather than financial gain.
Financial Compensation and Disgorgement:
Objective: Beyond structural corrections, Musk's legal actions include demands for financial remedies. He seeks disgorgement of profits that he claims were made in violation of the founding agreement, along with damages for his investments in OpenAI. The lawsuit also aims for a constructive trust on assets Musk believes were wrongfully gained by OpenAI and its affiliates.
Invalidation of Exclusive Licenses:
Objective: Musk is challenging the exclusive licensing agreements OpenAI has with Microsoft, particularly concerning the technology behind models like GPT-4, arguing these deals go against the nonprofit's mission of open-source development for the public good.
This strategy showcases a multifaceted approach, attempting to address both the ethical governance of AI and the business practices of OpenAI, reflecting Musk's broader concerns about the direction and control of AI technology in society.
+ Related content:
ft.com(1/9/25): Elon Musk calls on California and Delaware to force auction of OpenAI stake.
reuters.com (update; 1/10/25): [Excerpt] US supports Musk argument in OpenAI lawsuit. The U.S. Federal Trade Commission and Department of Justice were not expressing an opinion on the case, but offered legal analysis on aspects of the case ahead of a Tuesday hearing in Oakland, California. Musk co-founded OpenAI and owns AI startup xAI.
Marc Toberoff is the founding partner of Toberoff & Associates, and a leading attorney in the area of copyright and entertainment litigation. Called the "legal Man of Steel" and a "superhero to rights holders" by Variety, and a "brilliant crusader for the little guy" by The New York Times, Mr. Toberoff is a relentless, dedicated advocate of creators' rights. Mr. Toberoff has successfully represented numerous high-profile clients in a wide variety of intellectual property and entertainment transactional matters, ranging from the children of James Brown and Ray Charles, respectively, to the heirs of Jerry Siegel, Superman’s co-creator, and the family of Jack Kirby, the artistic genius behind most of Marvel’s superhero franchises.
🙂
☑️ #188 Jan 6, 2025
Currently losing money
@sama: insane thing: we are currently losing money on openai pro subscriptions! people use it much more than we expected.
🙂
☑️ #187 Dec 27, 2024
Why OpenAI’s Structure Must Evolve To Advance Our Mission
openai.com: [Excerpt] A stronger non-profit supported by the for-profit’s success.
The future
As we enter 2025, we will have to become more than a lab and a startup — we have to become an enduring company. The Board’s objectives as it considers, in consultation with outside legal and financial advisors, how to best structure OpenAI to advance the mission of ensuring AGI benefits all of humanity have been:
Make the non-profit sustainable. Our plan would result in one of the best resourced non-profits in history. The non-profit’s significant interest in the existing for-profit would take the form of shares in the PBC at a fair valuation determined by independent financial advisors. This will multiply the resources that our donors gave manyfold.
Equip each arm to do its part. Our current structure does not allow the Board to directly consider the interests of those who would finance the mission and does not enable the non-profit to easily do more than control the for-profit. The PBC will run and control OpenAI’s operations and business, while the non-profit will hire a leadership team and staff to pursue charitable initiatives in sectors such as health care, education, and science.
@cb_doge: BREAKING: Mark Zuckerberg’s company is siding with Elon Musk in a fight against the developer of ChatGPT.
Meta urges California Attorney General to stop OpenAI from becoming for-profit.
caption...
+ Related content:
wsj.com: [Excerpt] In a letter to Attorney General Rob Bonta dated Thursday, Meta said allowing the ChatGPT maker to become a for-profit company would set a dangerous precedent of allowing startups to enjoy the advantages of nonprofit status until they are poised to become profitable.
"OpenAI's conduct could have seismic implications for Silicon Valley. If OpenAI's new business model is valid, non-profit investors would get the same for-profit upside as those who invest the conventional way in for-profit companies while also benefiting from tax write-offs bestowed by the government,"
siliconangle.com (12/1/24) [Excerpts] Elon Musk tries to block OpenAI’s for-profit transition in latest legal tussle.
Technology entrepreneur Elon Musk has filed an injunction with a federal court, asking it to stop OpenAI from transforming itself into a fully for-profit business.
In the filing for a preliminary injunction Nov. 29, Musk, along with his artificial intelligence startup xAI Corp. and former OpenAI board member Shivon Zillis, is also seeking to stop the company from preventing its investors from funding competing AI firms.
Musk first sued OpenAI in March, filing a complaint in a San Francisco court that was later withdrawn, before being refiled several months later in a federal court. In that suit, attorneys for Musk, led by Marc Toberoff, complained that OpenAI has violated a number of federal racketeering, or RICO laws.
openai.com (12/13/24): [Excerpt] Elon Musk wanted an OpenAI for-profit.
Timeline of events:
November 2015: OpenAI started as a nonprofit, which Elon questioned
December 2018: Elon told us to raise “billions per year immediately or forget it”.
March 2019: We announced the capped-profit OpenAI LP, within the non-profit.
March 2023: Elon started his OpenAI competitor, xAI.
🙂
☑️ #185 Dec 6, 2024
OpenAI seeks to unlock investment by ditching ‘AGI’ clause with Microsoft
ft.com: [Excerpt] Start-up discusses removing provision to protect powerful technology from being misused for commercial purposes.
Under current terms, when OpenAI creates AGI — defined as a “highly autonomous system that outperforms humans at most economically valuable work” — Microsoft’s access to such a technology would be void. The OpenAI board would determine when AGI is achieved.
The start-up is considering removing the stipulation from its corporate structure, enabling the Big Tech group to continue investing in and accessing all OpenAI technology after AGI is achieved, according to multiple people with knowledge of the discussions. A final decision has not been made and options are being discussed by the board, they added.
The clause was included to protect the potentially powerful technology from being misused for commercial purposes, giving ownership of the technology to its non-profit board. According to OpenAI’s website: “AGI is explicitly carved out of all commercial and IP licensing agreements.”
@NewYorkTimesEvents (): The Next Frontier: Sam Altman on the Future of A.I. and Society.
Sam Altman discusses his corporate strategy at OpenAI, the transformative potential of artificial intelligence, and the ethical dilemmas it presents, in an interview with Andrew Ross Sorkin at the 2024 New York Times DealBook Summit.
🙂
☑️ #184 Dec 4, 2024
12 days of new things
@OpenAI: 12 days. 12 livestreams. A bunch of new things, big and small. 12 Days of OpenAI starts tomorrow.
+ Related content:
[New] 12 Days of OpenAI: Day 1:
⇢ ChatGPT Pro > OpenAI o1 and o1 pro mode in ChatGPT
openai.com: [Excerpt] Future’s 200+ brands will bring a broad range of news and lifestyle content to ChatGPT.
This content partnership builds on Future’s existing deployment of OpenAI’s technology. The publisher has developed chatbots so users can engage more deeply with content from Tom’s Hardware and Who What Wear. Future is also using OpenAI’s tools across multiple functions including sales, marketing, and editorial to boost productivity.
futureplc.com > Our Brands: Our content reaches one in three people in the UK and US through leading specialist media brands and events. We connect consumers worldwide with their passions and provide them with trusted, expert content.
🙂
☑️ #182 Dec 3, 2024
OpenAI Poaches 3 Top Engineers From DeepMind
wired.com: [Excerpt] The new hires, all experts in computer vision, are the latest AI researchers to jump to a direct competitor in an intensively competitive talent market.
OPENAI ANNOUNCED TODAY it has hired three senior computer vision and machine learning engineers from rival Google DeepMind, all of whom will work in a newly opened OpenAI office in Zurich, Switzerland. OpenAI executives told staff in an internal memo on Tuesday that Lucas Beyer, Alexander Kolesnikov, and Xiaohua Zhai will be joining the company to work on multimodal AI, artificial intelligence models capable of performing tasks in different mediums ranging from images to audio.
ft.com (): OpenAI targets 1bn users in next phase of growth. OpenAI is betting on a suite of new AI products, building its own data centres and a crucial partnership with Apple to supercharge its next phase of growth, as it targets reaching 1 billion users over the coming year.
The San Francisco-based group, whose popular ChatGPT chatbot has rocketed to 250mn weekly active users since its launch two years ago, plans to expand further through launching so-called AI “agents”, its own AI-powered search engine and ChatGPT’s integration with Apple devices. Read more
Unnamed sources briefed on the matter told the Financial Times that the company has started to hire advertising talent from big tech rivals.
🙂
☑️ #180 Nov 29, 2024
Media outlets, including CBC, sue ChatGPT creator
cbc.ca: [Excerpt] OpenAI accused of breaking copyright by using news articles to train chatbot.
A group of Canadian news outlets — including CBC/Radio-Canada, Postmedia, Metroland, the Toronto Star, the Globe and Mail and the Canadian Press — has launched a joint lawsuit claiming copyright infringement against ChatGPT creator OpenAI.
The lawsuit was filed in the Ontario Superior Court of Justice on Friday morning and is looking for punitive damages from OpenAI, along with payment of any profits that the company made from using news articles from the organizations.
OpenAI gets new $1.5 billion investment from SoftBank, allowing employees to sell shares in a tender offer
@thexcapitalist: OpenAI has no moat, it depends on Microsoft.
Don’t think Anthropic is in a better position.
Both of these companies would have gotten bankrupt if it wasn’t for the free cloud credits they got.
The real power lies with the cloud giants.
$MSFT, $AMZN and $GOOG pick winners.
🙂
☑️ #178 Nov 27, 2024 🔴 rumor
OpenAI gets new $1.5 billion investment from SoftBank, allowing employees to sell shares in a tender offer
cnbc.com: [Excerpt] OpenAI is allowing employees to sell roughly $1.5 billion worth of shares in a new tender offer to SoftBank, CNBC has learned.
The new financing will allow the Japanese tech conglomerate to get an even larger slice of the AI startup, and it will allow current and former OpenAI employees to cash out their shares, two people familiar with the matter told CNBC.
Employees will have until Dec. 24 to decide if they want to participate in the new tender offer, which has not previously been reported, one of the people said. The deal was spurred by SoftBank billionaire founder and CEO Masayoshi Son, who was persistent in asking for a larger stake in the startup after putting $500 million into OpenAI’s last funding round, one of the people said.
After 3 hours, OpenAI shut down Sora's early access temporarily for all artists
huggingface.co: ┌∩┐(◣◢)┌∩┐ DEAR CORPORATE AI OVERLORDS ┌∩┐(◣◢)┌∩┐
We received access to Sora with the promise to be early testers, red teamers and creative partners. However, we believe instead we are being lured into "art washing" to tell the world that Sora is a useful tool for artists.
ARTISTS ARE NOT YOUR UNPAID R&D
☠️ we are not your: free bug testers, PR puppets, training data, validation tokens ☠️
Hundreds of artists provide unpaid labor through bug testing, feedback and experimental work for the program for a $150B valued company. While hundreds contribute for free, a select few will be chosen through a competition to have their Sora-created films screened — offering minimal compensation which pales in comparison to the substantial PR and marketing value OpenAI receives.
▌║█║▌║█║▌║ DENORMALIZE BILLION DOLLAR BRANDS EXPLOITING ARTISTS FOR UNPAID R&D AND PR ║▌║█║▌║█║▌
Furthermore, every output needs to be approved by the OpenAI team before sharing. This early access program appears to be less about creative expression and critique, and more about PR and advertisement.
We are releasing this tool to give everyone an opportunity to experiment with what ~300 artists were offered: a free and unlimited access to this tool.
We are not against the use of AI technology as a tool for the arts (if we were, we probably wouldn't have been invited to this program). What we don't agree with is how this artist program has been rolled out and how the tool is shaping up ahead of a possible public release. We are sharing this to the world in the hopes that OpenAI becomes more open, more artist friendly and supports the arts beyond PR stunts.
We call on artists to make use of tools beyond the proprietary:
Open Source video generation tools allow artists to experiment with the avant garde free from gate keeping, commercial interests or serving as PR to any corporation. We also invite artists to train their own models with their own datasets.
Some open source video tools available are: Open Source video generation tools allow artists to experiment with avant garde tools without gate keeping, commercial interests or serving as a PR to any corporation. Some open source video tools available are:
However, as we are aware not everyone has the hardware or technical capability to run open source tools and models, we welcome tool makers to listen to and provide a path to true artist expression, with fair compensation to the artists.
Enjoy,
🙂
☑️ #176 Nov 26, 2024
Orange to expand open-source AI models to African regional languages for digital inclusion
Orange to accelerate digital inclusion in Africa through the incorporation of regional languages in AI Large Language Models (LLMs) for the first time.
Orange will fine-tune OpenAI’s open-source speech models and Meta’s openly available Llama 3.1 model to support regional African languages
Orange to provide resulting fine tuned AI models in open source for non-commercial use.
Orange is committed to play a key role in the development of Responsible AI in Africa as well as promoting open-source AI in Europe.
theinformation.com: [Excerpt] OpenAI is preparing to launch a frontal assault on Google. The ChatGPT owner recently considered developing a web browser that it would combine with its chatbot, and it has separately discussed or struck deals to power search feature...
Been thinking a lot about whether it's possible to stop humanity from developing Al.
I think the answer is almost definitely not.
If it's going to happen anyway, it seems like it would be good for someone other than Google to do it first.
Any thoughts on whether it would be good for YC to start a Manhattan Project for Al? My sense is we could get many of the top ~50 to work on it, and we could structure it so that the tech belongs to the world via some sort of nonprofit but the people working on it get startup-like compensation if it works. Obviously we'd comply with/aggressively support all regulation.
nytimes.com: [Excerpt] In a new legal filing, the Tesla chief executive accuses the A.I. start-up of undermining antitrust law.
The amended complaint, filed on Thursday in federal court in Northern California, makes new antitrust claims against OpenAI and adds defendants, including the tech giant Microsoft and the venture capitalist Reid Hoffman.
Microsoft is a close partner of OpenAI, after investing more than $13 billion in the start-up. Mr. Hoffman is a Microsoft board member and previously served on the board of OpenAI.
The new legal filing also adds two plaintiffs to the suit alongside Mr. Musk: his start-up xAI, which competes with OpenAI, and Shivon Zilis, a former OpenAI board member. Ms. Zilis is now an executive at Mr. Musk’s brain implant company Neuralink and the mother of three of his children.
u/AssistanceDry4748: I tried Searchgpt recently, and while it gave good results, I was wondering which impact could it have for writers.
If only summaries are displayed, and blog/website writers are not rewarded with views and better positioning, they may think that they don't need to feed the internet with useful information after all.
What do you guys think ? Is Searchgpt as it is viable for the long term ?
🙂
☑️ #170 Oct 25, 2024
Using SimpleQA to compare language models
@OpenAI: [Excerpt] Factuality is one of the biggest open problems in the deployment of artificial intelligence. We are open-sourcing a new benchmark called SimpleQA that measures the factuality of language models
+ Related content:
openai.com: [Excerpt] With SimpleQA, our goal was to create a dataset with the following properties:
High correctness. Reference answers to questions are supported by sources from two independent AI trainers, and questions were written in such a way that the predicted answers are easy to grade.
Diversity. SimpleQA covers a wide range of topics, from science and technology to TV shows and video games.
Challenging for frontier models. Compared to older benchmarks such as TriviaQA(opens in a new window)(2017) or NQ(opens in a new window) (2019), which have become saturated, SimpleQA was created to be a greater challenge for frontier models (e.g., GPT-4o scores less than 40%).
Good researcher UX. SimpleQA is intended to be fast and simple to run due to its concise questions and answers. Grading is also efficient whether through the OpenAI API or another frontier model API. Additionally, with 4,326 questions, SimpleQA should have relatively low variance as an evaluation benchmark.
U.S. military makes first confirmed OpenAI purchase for war-fighting forces
theintercept.com: [Excerpt] The Pentagon explored the AI software for research, but the new deal is the first by a combatant command whose mission is one of killing.
Less than a year after OpenAI quietly signaled it wanted to do business with the Pentagon, a procurement document obtained by The Intercept shows U.S. Africa Command, or AFRICOM, believes access to OpenAI's technology is "essential" for its mission.
The September 30 document lays out AFRICOM's rationale for buying cloud computing services directly from Microsoft as part of its $9 billion Joint Warfighting Cloud Capability contract, rather than seeking another provider on the open market. "The USAFRICOM operates in a dynamic and evolving environment where IT plays a critical role in achieving mission objectives," the document reads, including "its vital mission in support of our African Mission Partners [and] USAFRICOM joint exercises."
The document, labeled Controlled Unclassified Information, is marked as FEDCON, indicating it is not meant to be distributed beyond government or contractors. It shows AFRICOM's request was approved by the Defense Information Systems Agency. While the price of the purchase is redacted, the approval document notes its value is less than $15 million.
Former OpenAI Researcher Says the Company Broke Copyright Law
@suchirbalaji: I recently participated in a NYT story about fair use and generative AI, and why I'm skeptical "fair use" would be a plausible defense for a lot of generative AI products. I also wrote a blog post (https://suchir.net/fair_use.html) about the nitty-gritty details of fair use and why I believe this.
To give some context: I was at OpenAI for nearly 4 years and worked on ChatGPT for the last 1.5 of them. I initially didn't know much about copyright, fair use, etc. but became curious after seeing all the lawsuits filed against GenAI companies. When I tried to understand the issue better, I eventually came to the conclusion that fair use seems like a pretty implausible defense for a lot of generative AI products, for the basic reason that they can create substitutes that compete with the data they're trained on. I've written up the more detailed reasons for why I believe this in my post. Obviously, I'm not a lawyer, but I still feel like it's important for even non-lawyers to understand the law -- both the letter of it, and also why it's actually there in the first place.
That being said, I don't want this to read as a critique of ChatGPT or OpenAI per se, because fair use and generative AI is a much broader issue than any one product or company. I highly encourage ML researchers to learn more about copyright -- it's a really important topic, and precedent that's often cited like Google Books isn't actually as supportive as it might seem.
Feel free to get in touch if you'd like to chat about fair use, ML, or copyright -- I think it's a very interesting intersection. My email's on my personal website.
+ Related content:
nytimes.com: [Excerpts] Former OpenAI Researcher Says the Company Broke Copyright Law. Suchir Balaji helped gather and organize the enormous amounts of internet data used to train the startup’s ChatGPT chatbot.
Mr. Balaji, 25, who has not taken a new job and is working on what he calls “personal projects,” is among the first employees to leave a major A.I. company and speak out publicly against the way these companies have used copyrighted data to create their technologies. A former vice president at the London start-up Stability AI, which specializes in image- and audio-generating technologies, has made similar arguments
mercurynews.com (update; 12/13/24): [Excerpt] OpenAI whistleblower found dead in San Francisco apartment. Suchir Balaji, 26, claimed the company broke copyright law.
In a Nov. 18 letter filed in federal court, attorneys for The New York Times named Balaji as someone who had “unique and relevant documents” that would support their case against OpenAI. He was among at least 12 people — many of them past or present OpenAI employees — the newspaper had named in court filings as having material helpful to their case, ahead of depositions.
🙂
☑️ #167 Oct 22, 2024
OpenAI Hires Former White House Official as Its Chief Economist
nytimes.com: [Excerpt] Aaron Chatterji was chief economist at the Commerce Department under President Biden and served on President Obama’s Council of Economic Advisers.
The addition of a chief economist is indicative of OpenAI’s enormous ambition and where its executives see their company in the tech industry’s pecking order. Silicon Valley giants like Google and Facebook hired seasoned economists early in their transformations from promising start-ups into trillion-dollar companies whose technologies changed global markets.
Transition to a for-profit company: OpenAl is advised by Goldman Sachs
wsj.com: [Excerpt] The $14 Billion Question Dividing OpenAI and Microsoft. The two companies have hired investment banks to help negotiate how much equity Microsoft gets when OpenAI becomes a for-profit company.
Bain & Company announces expanded partnership with OpenAI to accelerate delivery of AI solutions and meet fast-growing client needs
bain.com: [Excerpt] Deepening of collaboration sees Bain establish a dedicated OpenAI Center of Excellence to drive and deliver AI innovation for clients and maximize value of clients’ AI investments.
During this time, Bain has worked with OpenAI to embed multiple AI solutions into clients’ operations and deliver concrete business results across a range of use cases. In doing so Bain has supported clients in changing and improving processes, operating models, technology architectures, talent and data assets. Bain will continue to leverage OpenAI’s fast-developing products and platform in its offerings to clients on AI transformation consulting, which encompasses AI strategy development, process change, workforce and organizational development, and technology foundations, guiding leaders through their companies’ AI journeys. Under their expanded partnership, the two firms will also work closely through a regular series of joint industry roundtables and events to showcase the impact of their collaborations in delivering transformational results for clients around the world.
Documents show OpenAI’s long journey from nonprofit to $157B valued company
apnews.com: [Excerpt] In general, nonprofit experts agree that OpenAI has gone to great lengths to arrange its corporate structure to comply with the rules that govern nonprofit organizations. OpenAI’s application to the IRS appears typical, said Andrew Steinberg, counsel at Venable LLP and a member of the American Bar Association’s nonprofit organizations committee.
If the organization’s plans and structure changed, it would need to report that information on its annual tax returns, Steinberg said, which it has.
“At the time that the IRS reviewed the application, there wasn’t information that that corporate structure that exists today and the investment structure that they pursued was what they had in mind,” he said. “And that’s okay because that may have developed later.”
Before we get to today's column, please read this phenomenal piece from Aaron about Microsoft CEO Satya Nadella's market analysis methods. Hint: they involve an absurd number of meetings and calls with people outside his company. It's a leadership masterclass.
Onto today's issue...
When we told you in July that OpenAI would probably lose $5 billion this year, we also explained how the company reminded us of Uber, a previous Silicon Valley startup darling that endured heavy losses en route to a sustainable business —eventually.
theinformation.com (10/9/24): [Excerpt] OpenAI Projections Imply Losses Tripling to $14 Billion in 2026.
OpenAl's newest investors have signed up for a bumpy and expensive ride. The company's projections suggest it won't turn a profit until 2029, when its revenue would hit $100 billion.
Before it gets to that point, losses could rise as high as $14 billion in 2026, nearly triple this year's expected loss, according to an analysis of data contained in OpenAI financial documents viewed by The Information. This estimate doesn't include stock compensation, which is one of OpenAI's biggest expenses. although not one it pavs in cash.
We’re opening offices in NYC, Seattle, Paris, Brussels, and Singapore, alongside our growing San Francisco, London, Dublin, and Tokyo offices. Want to join us? https://openai.com/careers/
🙂
☑️ #161 Oct 8, 2024
Look what showed up at our doorstep
@OpenAI: Look what showed up at our doorstep. Thank you to @nvidia for delivering one of the first engineering builds of the DGX B200 to our office.
Foundation of NVIDIA DGX BasePOD and NVIDIA DGX SuperPOD
Includes NVIDIA AI Enterprise and NVIDIA Base Command software Datasheet
🙂
☑️ #160 Oct 4, 2024
Breakingviews: OpenAI’s $157 bln valuation requires hand waving
lipperalpha.refinitiv.com: [Excerpt] It’s possible OpenAI is worth $157 billion; it just requires a bit of hand waving. Technology giants, venture capital firms, and the usual suspects in the hedge fund and investment world piled into the company started by Sam Altman to give the artificial intelligence company $6.6 billion in new funding. Assuming these investors want a return commensurate with risk, say 20% annually for a decade, OpenAI’s value needs to grow to $1 trillion. That doesn’t immediately compute.
OpenAI estimates revenue will triple next year to $11.6 billion, and Altman thinks revenue could reach $100 billion by 2029 according to the New York Times. Few companies grow that fast for that long, but in the tech world, it’s possible. Meta Platforms was growing at about the same pace as OpenAI in 2009, and over the following four years revenue grew nine times bigger. If OpenAI achieves similar growth, it would slightly exceed Altman’s target.
rl3: This was just published the other day and goes in-depth about your question:
fortune.com (10/1/24): [Excerpt] Before Mira Murati’s surprise exit from OpenAI, staff grumbled its o1 model had been released prematurely.
The same day Murati said she would be going, two other senior staffers, Bob McGrew, chief research officer, and Barret Zoph, vice president of research who had appeared along with Murati in the GPT4-o launch webcast, also announced they were stepping down. From the outside, it looked as though the company was once again at risk of imploding at a time when it wanted to sell investors on the idea that it was maturing into a more stable, if still fast-growing, organization.
3. Other firms are offering huge incentives to OpenAI employees, and engineers are doing what engineers always do: job-hopping to jump a rank or two in the job ladder. From last year, but still relevant IMO: https://techcrunch.com/2023/11/20/openai-ai-talent-poaching-...
4. People are concerned that OpenAI's future is not as bright as it seems given its current (objective) technical dominance, a discussion centering around terms like "moat" and "propriety data" and "open source vs. closed source". Some challenges facing the company include: quite uncertain lawsuits of existential size (https://www.nytimes.com/2023/12/27/business/media/new-york-t...), the fact they're losing $5B/y without a proven path out of that (https://www.datacenterdynamics.com/en/news/openai-training-a...), and, on a meta level, your question itself -- they've lost basically all of their top scientists.
AI Hype or Reality? Shifts in Corporate Investment after ChatGPT
stlouisfed.org: [Excerpt] Using Text-as-Data Analysis in Earnings Calls.
Earnings calls are quarterly meetings in which executives of publicly traded companies discuss the financials and current operations of their firms and factors that may impact future performance. For our analysis, we parsed transcripts of 185,999 earnings calls from 7,047 U.S. firms between the second quarter of 2008 and the first quarter of 2024. To learn more about how we conducted our text-as-data analysis, refer to our previous post. In brief, however, we measured AI conversation in earnings calls by identifying sentences that contained keywords such as “machine learning” or “chatgpt.” We then identified sentiment in sentences that mentioned AI from positive- or negative-tone keywords, such as “advantageous” on one hand and “dangers” on the other. Finally, we computed net AI sentiment by subtracting the number of negative-sentiment sentences from that of positive-sentiment sentences for each earnings call.
openai.com: [Excerpt] New Credit Facility Enhances Financial Flexibility.
In addition to securing $6.6 billion in new funding from leading investors, we have established a new $4 billion credit facility with JPMorgan Chase, Citi, Goldman Sachs, Morgan Stanley, Santander, Wells Fargo, SMBC, UBS, and HSBC. This is a revolving credit facility that is undrawn at closing.
This means we now have access to over $10 billion in liquidity, which gives us the flexibility to invest in new initiatives and operate with full agility as we scale. It also reaffirms our partnership with an exceptional group of financial institutions, many of whom are also OpenAI customers.
openai.com: [Excerpt] We’ve raised $6.6B in new funding at a $157B post-money valuation to accelerate progress on our mission. The new funding will allow us to double down on our leadership in frontier AI research, increase compute capacity, and continue building tools that help people solve hard problems.
ft.com (update; 10/3/24): [Excerpt] OpenAl poses new investors an intelligence test. Start-up has another $6.6bn of cash, but providers will have had to grapple with at least 4 flavours of complexity.
ft.com (10/2/24): [Excerpt] OpenAl asks investors not to back rival start-ups such as Musk's xAI. Sam Altman-led group wants exclusive arrangement as it secures $6.6bn funding round.
🙂
☑️ #155 Oct 2, 2024 🔴rumor
How OpenAI CFO Sarah Friar Is Keeping Startup Flush With Cash
theinformation.com: [Excerpt] Friar once made Jack Dorsey's Square presentable to investors. Now she's helping Sam Altman with a gargantuan $6.5 billion fundraising effort for OpenAI to help with its seemingly unquenchable need for capital.
At Square, Sarah Friar was the grownup who helped bring the fintech's otherworldly CEO, Jack Dorsey, down to earth for investors. Now she has a shot at doing something similar for Sam Altman's OpenAl—if she can last long term at the chaotic artificial intelligence startup.
Since arriving at OpenAl as chief financial officer in June, Friar has polished a management presentation for investors to make it "dead simple" compared to earlier fundraising pitches from the company, according to one person who saw it. The pitch hinges largely on mouthwatering comparisons that show OpenAI is one of tech's fastest-growing consumer products, with the fastest revenue growth in tech history, comparable only to the likes of Google and Facebook, another person said.
OpenAI is forecasting revenues that would nearly triple to $11.6 billion next year and then double again to $25.6 billion, according to the person who saw the presentation. To get there, the startup has been burning hundreds of millions of dollars a month.
wsj.com: [Excerpt] Company behind ChatGPT is aiming to raise around $6.5 billion in funding set to close next week.
Apple is no longer in talks to participate in an OpenAI funding round expected to raise as much as $6.5 billion, an 11th hour end to what would have been a rare investment by the iPhone maker in another major Silicon Valley company.
Apple recently fell out of the talks to join the round, which is slated to close next week, according to a knowledgeable person.
OpenAI to Become For-Profit Company (9/25/24): [Excerpt] Planned restructuring comes amid personnel upheaval including resignation of chief technology officer
🙂
☑️ #152 Sep 26, 2024
The last eight years of OpenAl has been a humbling and awe-inspiring journey
The last eight years of OpenAl has been a humbling and awe-inspiring journey. The small non-profit I joined in January 2017 has become the most important research and deployment company in the world.
I have truly enjoyed working alongside an entire company full of brilliant, committed individuals - there is no other place like this in the world. I'm immensely proud of the work that our research team has done over these years, from our early achievements in RL to pioneering LLMs to building the first multimodal generative models to transforming the world with ChatGPT.
It is time for me to take a break. There is no better capstone to my work here than shipping 01 to the world.
Moving forward, Mark Chen will be leading the research team as the SVP alongside Jakub as the Chief Scientist. I will remain to support Mark, Jakub, and the team during the transition for the next two months. I have great confidence in their leadership to take OpenAl's research to AGI and beyond. I can't wait to see what this team does next.
This was a very difficult decision as I have has such an incredible time at OpenAI. I got to join right before ChatGPT and helped build the post-training team from scratch with John Schulman and others. I feel so grateful to have gotten the opportunity to run the post-training team and help build and scale ChatGPT to where it is today. Right now feels like a natural point for me to explore new opportunities outside of OpenAI. This is a personal decision based on how I want to evolve the next phase of my career.
I am very grateful for all the opportunities OpenAI has given me and all the support I have gotten from OpenAI leadership such as Sam and Greg. I am in particular grateful for everything Bob has done and for being an excellent manager and colleague to me over my career at OpenAI. The post-training team has many many talented leaders and is being left in good hands.
OpenAI is doing and will continue to do incredible work and I am very optimistic about the future trajectory of the company and will be rooting everybody on.
🙂
☑️ #151 Sep 26, 2024
OpenAI and GEDI announce strategic partnership to bring Italian-language news content to ChatGPT
gedi.it: [Excerpts] 26 September, 2024 - Italian media group, GEDI, and OpenAI, an AI research and deployment company behind ChatGPT, have today announced a strategic partnership to bring Italian-language content from GEDI’s portfolio of high-quality news outlets to OpenAI’s users.
"The partnership signed with OpenAI is part of GEDI’s digital transformation journey and recognizes its leadership in producing high-quality content within the Italian media landscape. From today, ChatGPT users will be able to rely on articles and in-depth analyses from our publications to obtain top quality information on a wide range of topics, with a special focus on the Italian context. This agreement also allows GEDI to reach a broader international audience, thanks to the advanced translation capabilities developed by ChatGPT."
