Altman details Musk's OpenAI fallout, says nonprofit was 'left for dead'

OpenAI CEO Sam Altman testified in the Musk v. Altman trial on Tuesday, where he tried to make his central claim clear to the jury: He didn't steal a charity, but Elon Musk abandoned one.

Altman, wearing a blue suit and tie, spoke from the witness stand in federal court in Oakland, California over the course of about four hours. He said that Musk, who co-founded OpenAI alongside him in 2015, did not keep his promises and eventually deserted the young startup as it was trying to chart out an uncertain future.

"We were kind of left for dead," Altman testified.

Musk sued OpenAI, Altman and the company's president, Greg Brockman, in 2024, alleging they went back on their vow to keep the artificial intelligence company a nonprofit and follow its charitable mission. He argued that the roughly $38 million he donated to OpenAI was used for unauthorized commercial purposes.

Altman testified on Tuesday that he did not make any commitments to Musk about OpenAI's corporate structure.

Tense negotiations between co-founders

Much of the trial, which kicked off late last month, has centered around a series of contentious negotiations that took place between Musk, Altman, Brockman and Ilya Sutskever, another OpenAI co-founder, in 2017 and 2018.

The executives agreed they needed to raise more money for computing resources, and they debated a range of potential corporate structures, including for-profit options, that could help them do so.

The talks ultimately collapsed without a clear resolution, and Musk left OpenAI's board in February of 2018.

Altman testified that Musk's departure caused OpenAI employees to worry about how the company would be funded, and that some were concerned Musk would seek "vengeance." But Altman said Musk's exit was also a "morale boost" for some researchers, who had been "demotivated" by his management tactics.

"I don't think Mr. Musk understood how to run a good research lab," Altman said.

Musk continued communicating with Altman, Brockman and Sutskever in 2018, months after he formally left the startup's board. He said the company had no chance of succeeding.

"My probability assessment of OpenAI being relevant to DeepMind/Google without a dramatic change in execution and resources is 0%. Not 1%. I wish it were otherwise," Musk wrote in an email that December. "Even raising several hundred million won't be enough. This needs billions per year immediately or forget it."

Altman said Tuesday that Musk's comment was "burned into my memory."

OpenAI established a for-profit subsidiary following Musk's departure, which is now valued at more than $850 billion by private investors.

Musk testified in April that OpenAI's for-profit subsidiary became the "tail wagging the dog," and he repeatedly accused Altman and Brockman of trying to "steal a charity." Altman pushed back on that notion, testifying that what Musk really cared about was control.

Altman said that Musk felt very strongly about having total control over OpenAI, at least initially. He said that was partially because Musk didn't trust other people to make decisions, and that Musk had "long-since decided" he was only going to work on companies that he controlled.

"I was extremely uncomfortable with it," Altman said.

Musk testified in April that he did seek majority control of OpenAI initially, but that his stake in the company would have diluted over time. He also said he was not completely opposed to OpenAI having a for-profit subsidiary, but that it became a problem when it overshadowed the nonprofit.

During negotiations, Musk suggested merging OpenAI with Tesla, his electric automaker, as a way to fuse more capital into the company. He offered Altman a Tesla board seat to try and convince him to make the move.

Altman said he didn't think it was the right fit, and he worried that the nonprofit would have effectively been destroyed in the process.

"Tesla is a car company, and it does not have the mission of OpenAI," Altman said. "I don't think we would've had the ability to ensure that the mission was acted on."

Musk's lawyer tried to paint Altman as untrustworthy

Musk's lawyer Steven Molo, cross-examined Altman and tried to paint the OpenAI chief as unreliable and dishonest. He opened his line of questioning by asking Altman whether he is "completely trustworthy."

"I believe so," Altman said.

"But you don't know whether you're completely trustworthy?" Molo responded.

"I'll just amend my answer to yes," Altman said.

Molo asked Altman about a number of people who have expressed concerns with his behavior over the years, including Dario Amodei, a former OpenAI employee who went on to found the company's chief rival, Anthropic. Molo said Amodei had accused Altman of misrepresenting the terms of an investment to him.

"Dario has accused me of many things," Altman testified.

Molo also pressed Altman about some of the board members who briefly ousted him from his role at OpenAI in 2023. The board said at the time that Altman was "not consistently candid in his communications" with them.

Altman spoke at length about his removal throughout his testimony. He said he was "completely caught off guard" by the board's decision, and that he was upset, angry and hurt during the chaotic few days before he returned to OpenAI.

He said he did not get much of an explanation about why he was fired, other than the board's assertion that he had not been candid with them.

"I had poured the last years of my life into this," Altman said. "I was watching it about to be destroyed."

Closing arguments in the trial are slated for Thursday, and the nine-person jury will begin deliberating next week. The jury in this case is advisory, which means the final outcome will ultimately rest with Judge Yvonne Gonzalez Rogers.