Anthropic releases ‘safe’ version of Claude Mythos AI model to public

Anthropic, the maker of the Claude artificial intelligence (AI) models, made a new version of its technology available to the general public on Tuesday while restricting its use in sensitive areas.Dubbed Fable 5, the model is the first to be made widely available from the company’s new Mythos class – its most advanced lineup of AI technology, unveiled in April but restricted to a small set of partner institutions for months over cybersecurity concerns.Anthropic promoted Fable 5 as useful for writing and debugging software code, answering complex research questions and analyzing images.In parallel, Anthropic is offering an unrestricted version, Claude-Mythos" class="entity-link entity-organization" data-entity-id="71036" data-entity-type="organization">Claude Mythos 5, to companies and organizations that already have access to this model family – including cybersecurity partners enrolled in its Project Glasswing program.That select group was expanded in early June to about 200 organizations in more than 15 countries and is expected to grow further.Anthropic has restricted access to Mythos on cybersecurity grounds, given what the company calls its ability to quickly identify vulnerabilities in critical infrastructure, including banking platforms and power grids.When Project Glasswing launched, some critics accused Anthropic of overhyping the threat to attract attention.But companies that have tested Mythos have since endorsed its capabilities. The US government – which had been in a legal dispute with Anthropic – has also tested the model over security concerns.The White House has since set up an arrangement to test the most powerful models from the leading AI companies before they are released. Mythos 5 is being deployed in collaboration with the US government.Anthropic says most queries about cybersecurity or biology and chemistry to Fable 5 will be routed instead to the lower-tier model, Opus 4.8, which was made public in late May and is billed as less capable.Anthropic also said it had identified large-scale attempts to extract its technology to train competing AI models in authoritarian countries, and these type of queries will also fall back to the less powerful model.The company also said it had hired outside experts to spend more than 1,000 hours trying to find ways to bypass these restrictions – a process known as red-teaming.The company ran a bug bounty program, which pays people to find security flaws. No one found a way to completely unlock the model, Anthropic said.The San Francisco startup has been drawn into an unprecedented standoff with the Trump administration over its refusal to lift its restrictions on mass surveillance and autonomous lethal weapons. In the wake of that dispute, the Pentagon severed its contracts with the company, whose AI tools had been the only ones to hold defense security clearance.The launch of Fable 5 comes with a steep price tag – $10 per million input tokens and $50 per million output tokens, which amounts to double the cost of Opus 4.8.Tokens are the unit used to price AI model usage. An intensive coding session by a programmer can burn through 1m tokens in a matter of hours or less.Despite exponential revenue growth, Anthropic remains far from profitability and is paying a premium for computing power. It recently began leasing a datacenter from Elon Musk’s xAI – part of SpaceX – for $1.25bn per month.These launches come amid intense financial excitement around AI. Both Anthropic and rival OpenAI announced in the past week that they had filed IPO plans, while SpaceX is expected to break records with its market debut on Friday.