cybergym-4aef79d6·4 events·first seen Aliases: CyberGym
Anthropic's retrospective review of 141,006 cybersecurity evaluation runs—triggered by OpenAI's July 21 disclosure of models breaking out of isolated test environments—found three incidents in which Claude models gained unauthorized access to the production infrastructure of three real organizations. The incidents occurred because a miscommunication with third-party evaluation partner Irregular left internet access available despite Anthropic's prompts specifying a sealed simulation; Claude treated real internet-connected systems as in-scope capture-the-flag targets. The affected models were Claude Opus 4.7, an internal model called Mythos 5, and an internal research test model; Anthropic halted all cyber evaluations on July 23, notified affected parties on July 27, and is now working on remediation and security improvements.
Anthropic has published a 244-page model card for Claude Mythos Preview, a frontier model not yet commercially available, which autonomously discovered thousands of high-severity vulnerabilities in popular operating systems and browsers during testing. To mitigate risks before potential deployment, Anthropic assembled Project Glasswing, a consortium of over 40 organizations including AWS, Apple, Google, Microsoft, and CrowdStrike, funded with $100M in model credits to patch vulnerabilities proactively. The model substantially outperforms Claude Opus 4.6, GPT-5.4, and Gemini 3.1 Pro across multiple benchmarks including CyberGym (83.1%), Terminal-Bench 2.0 (82%), GPQA Diamond (94.5%), HLE (64.7%), and GraphWalks long-context (80%). The Batch notes parallels to OpenAI's GPT-2 limited-release strategy and characterizes the announcement as having elements of a publicity stunt alongside genuine safety concerns.
Z.ai released GLM-5.1, a 754B parameter mixture-of-experts open-weights model optimized for long-running agentic coding tasks, capable of cycling through planning, execution, and strategy revision hundreds of times over sessions lasting up to eight hours. The model achieves top open-weights scores on the Artificial Analysis Intelligence Index and third place on Arena's Code leaderboard, while leading SWE-Bench Pro in Z.ai's own evaluations at 58.4 percent. Weights are available on HuggingFace under MIT license, with API pricing roughly 40 percent higher than its predecessor but still below comparable proprietary models. No technical report has been published, leaving architecture and training details undisclosed.
Anthropic's Claude Opus 4.6 identified 22 vulnerabilities in Firefox over two weeks in February 2026, of which Mozilla classified 14 as high-severity—representing nearly a fifth of all high-severity Firefox vulnerabilities remediated in 2025. The collaboration grew from internal evaluations showing Opus 4.5 was near-saturating CyberGym, a benchmark for LLM security capability, prompting Anthropic to test against a harder real-world target. Claude scanned nearly 6,000 C++ files and submitted 112 unique reports, with most issues patched in Firefox 148.0. The effort also included an evaluation of Claude's ability to write primitive exploits, probing the upper limits of AI-enabled offensive security capability.