Path to an AI Mythology
Anthropic, the Department of War, a Sovereign Wealth Fund, Mythos and Sam Altman.
As SpaceX, OpenAI and Anthropic IPOs approach in the days and months ahead, how we define the narrative around the future of AI is also taking shape. With Anthropic expanding access to its new class of LLM called Mythos to more organizations, the U.S. Department of War appears to be using Mythos for Cybersecurity attacks, reports the FT.
In recent weeks several significant seed rounds have been given to AI labs in the U.S. working on various aspects of recursive self-improving AI capabilities, or RSI. We have to conclude that Mythos as an LLM step-up might represent the first RSI-native Model. If Anthropic’s framing is correct, we are heading into unchartered territory.
Claude 4.8 already seemed like solid advancements but the Mythos class appears relatively distinguished compared to its competitors at Google, OpenAI or China. This is giving Anthropic a feeling of grandeur heading to its landmark IPO that might end up being the highlight of these Mega IPOs of 2026. Now in a blog post on its website on Thursday, Anthropic wrote about the risks of AI progressing to a point where it could improve itself autonomously.
Anthropic reported a landmark blog titled When AI Builds Itself, while the U.S. Government is discussion about taking equity stakes in the biggest AI companies. That is for real, Senior U.S. officials held preliminary discussions with major AI companies about the potential for the government to buy some shares in their firms. These are unprecedented and gravely risky endeavors as Nation States seek to mould AI in their image.
OpenAI CEO Sam Altman has discussed the idea with government officials since President Donald Trump began his second term, the report said. Sam Altman and Bernie Sanders have different ideas on how that could look. This is in sync with Trump and his financial elite friends to create a Sovereign Wealth Fund for the United States. Anthropic is not having conversations with the administration about providing equity to the government and it’s not clear what Sam Altman or OpenAI’s motives are to enter into such a deal.
A White House meeting is reportedly being set up with leading AI firms to explore the concept
Anthropic’s Mythos has raised concerns that new AI models might be capable of, including and especially in cybersecurity. Anthropic confidentially filed its IPO prospectus with the SEC and said it will offer Mythos to the European Union along with an additional 150 partners in 15 countries. Mythos is becoming more than just a frontier model however, it’s becoming part of a larger debate around what recursive self-improving AI might do if it’s real across industries.
Anthropic’s cryptic Tweets are also unsettling at a time when Anthropic is clearly working more closely with the Department of War while being held semi-hostage with a rather nefarious designation as a supply-chain risk.
Defense Secretary Pete Hegseth has denied Anthropic’s request to reconsider the AI startup’s designation as a national security risk, the Pentagon told the D.C. Circuit Court of Appeals on Thursday.
It appears like the Trump Administration has a special relationship with Sam Altman and OpenAI and is trying to supress whatever Anthropic represents. If Mythos is being used for cybersecurity offense (supposedly against China) then this is not a good sign of AI becoming a geopolitical risk in an era of more automated systems in National defense.
