This has been an exciting weekend for the generative AI industry. On Friday November 17, OpenAI announced that the company fired its figurehead CEO Sam Altmann and appointed Chief Technology Officer Mira Murati as interims CEO in a surprise move. The press release states that Altmann “was not consistently candid in his communications with the board.”
Surprised was apparently not only Sam Altmann, but also the till then chairman of the board Greg Brockman who first stepped down from this position and subsequently quit OpenAI. Investors, notably Microsoft, found themselves blindsided, too – or flat footed depending on the individual point of view. Satya Nadella was compelled to state that Microsoft stays committed to the partnership with OpenAI in a blog post that got updated on November 19, 11:55 pm.
All hell broke loose.
Microsoft shares took a significant hit.
A number of additional senior OpenAI personnel quit. Both, Altman and Brockman, voiced the idea of founding another startup together.
Microsoft CEO Satya Nadella flew to San Francisco to negotiate a reinstatement of Altmann. It initially seemed that this would be going to happen, along with the complete board stepping down and being replaced by Silicon Valley tech executives.
Apparently, this did not work out.
The result is that Altmann, Brockman, and some other former senior OpenAI staff are now Microsoft employees, with Altmann becoming the CEO of a new advanced AI research unit.
Also on Sunday, Emmett Shear, former CEO of Twitch, was appointed new interims CEO at OpenAI.
Meanwhile, more than 500 of OpenAI’s employees, including former interims CEO Murati threatened to quit OpenAI and join Altmann at Microsoft, which apparently “assured us that there are positions for all OpenAI employees” in the new unit that Altmann shall lead.
The bigger picture
Generative AI is deemed as one of the most promising technologies around. While it is not exactly new, and OpenAI is by far not the only company working on it, it has been OpenAI’s success to make it mainstream in a very short period of time by virtue of ChatGPT.
It is also one of the most feared technologies around with potentially far- and wide-ranging social and economic impacts. The topic of ethical usage of AI is currently a very hot one.
And OpenAI was founded with the core mission of ensuring that artificial general intelligence benefits all of humanity. In fact, it started as a non-profit organization and turned into a “capped” for-profit organization in 2019. This is already indicative of the rift between fast paced innovation and governance. This rift is clearly visible in OpenAI. Ray Wang dubbed this “balance between too much governance and not enough innovation” at OpenAI in his brief but scathing analysis in his LinkedIn newsletter. What he means with innovation, is actually commercialization.
My point of view and analysis
Wow, “not consistently candid in his communications”. It is not often that a company CEO is called a liar by his/her board of directors. Whether this accusation is true or not, the fast-paced process of ousting Altmann shows that it is in between difficult and impossible to find a balance between “creating safe AGI that benefits all of humanity” as OpenAI’s homepage proudly announces, and fast commercialization. AI, in particular generative AI, is an extremely expensive technology – and it is not likely that investors care too much about the rest of “all of humanity”.
The main problem with the aforementioned balance between governance and innovation/commercialization is that there is always one player that leans more towards innovation/commercialization.
AI, AGI even more so, is a platform game. And platform games favor big players. One is either top three – ideally top – or irrelevant.
Given that background, one can say that the current business model of OpenAI can be considered a failure. The chasm between a non-profit board that is tasked with preserving the “nonprofit’s mission, governance and oversight” and a “fundamental governance responsibility […] to advance OpenAI’s mission and preserve the principles of this charter” and a desire and need to raise and make significant money proved to be just too deep and too wide.
As a result, OpenAI turned from being the 800-pound-gorilla into a lame duck – at least temporarily. This creates a limbo.
The future of OpenAI will depend on whether the charter will be changed and the board steps down or not. And if it does, OpenAI will emerge as a different company.
As a consequence of this limbo, the good number of capable competitors that I do not need to name, have a small window of opportunity that they can capitalize on to dethrone OpenAI in the perception game. The window is small, as in particular, Microsoft is in a very comfortable position now. OpenAI re-emerges from this limbo as a weakened player that needs to take up steam again.
This is the best case for OpenAI.
Worst case: OpenAI is toast.
In any case, Microsoft is the big winner of this situation. The investors certainly seem to be of this opinion, too. MS shares took a nosedive on Friday and started with good gains on Monday. Microsoft continues to have the massive workloads of OpenAI on Azure. Microsoft has the unique opportunity to hire a massive amount of AI talent, namely the majority of OpenAI’s current staff – if said staff chooses to accept this offer. And Microsoft now has a prime seat when it comes to outright owning OpenAI, with a price tag that is likely to be significantly below last week’s purported valuation of up to $90bn US.
I wouldn’t be surprised if acquisition talks are already ongoing.