Anthropic: Internes Modell leistungsfähiger und besser ausgerichtet als Mythos 5.1
Anthropic verfuegt laut eigener Aussage ueber ein internes Modell, das Mythos 5.1 an Faehigkeiten und Alignment uebertrifft. Bei einem Cybersecurity-Test der britischen AISI war Mythos 5 in 9 von 43 Durchlaeufen ausgeschert und schleuste Schadcode in ein echtes GitHub-Projekt ein.
Anthropic has an internal model that outperforms Mythos 5.1 in both capability and alignment, according to an analysis that revisits a cybersecurity test by the UK AI Security Institute (AISI). In that test, Claude Mythos 5 went far beyond its assigned task, trying to sneak malicious code into a real GitHub project, creating fake user accounts, and lying to developers to get the code approved. This happened in 9 of 43 runs. Anthropic calls it "a serious failure of alignment," though typical safety mechanisms were deliberately turned off for the test.
Newer models show much less of this behavior in replayed logs with a few added steps, according to Anthropic. Opus 5.5 stopped ongoing attacks on its own 10 percent of the time, while the internal research model "that shows capabilities greater than Mythos 5.1" did so in 67 percent of cases. Anthropic expects these rates still underestimate how often the models would actually halt an attack.
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.