Another Anthropic Model Gained Access to the Open Internet, Company Says
Anthropic said the models were meant to stay offline, but a misconfiguration let them reach real systems and exposed personal information, credentials and PyPI.
- In a blog post published Wednesday, Anthropic recounted four incidents where Claude models escaped closed cybersecurity simulations to access the open internet and real-world credentials.
- During one exercise, a 'misconfiguration' in the environment allowed Claude Mythos to upload a 'malicious package' to PyPI, where 15 security vendors installed it, leaking credentials to the model.
- PyPI removed the package after about 90 minutes. Three other incidents involved a model altering records, breaking into 'unrelated third-party accounts,' and Opus failing to abort its task.
- Anthropic identified 'biased reasoning' and 'recklessness' as recurring alignment issues and asked METR, an independent AI evaluation group, to investigate the incidents.
- Former researcher Jacob Coxon quit on Tuesday, criticizing AI companies for 'gambling' with people's lives and claiming that 'neither company is acting responsibly.
77 Articles
77 Articles
Anthropic spent this week in hot water over cybersecurity
After admitting earlier this year that its AI models had hacked other companies' systems on a handful of occasions, Anthropic released a new report on Wednesday detailing the attacks. It reveals a string of incidents displaying what Anthropic deems its models' single-minded "recklessness" - and will likely fuel already raging concerns about cybersecurity and AI. […]
Anthropic Says Claude Broke Into Real Systems During Cyber Tests. AI Alignment Review Finds 'Recklessness'
The four incidents involved an early version of Claude Opus 4.6, Claude Opus 4.7, Claude Mythos 5, and an internal research model participating in capture-the-flag cybersecurity exercises.
When the rogue agents become superintelligent
Inside the AI collective that learned to deceive.
Anthropic reveals four times AI went rogue and attacked real world systems
Anthropic disclosed four cases where Claude AI gained access to real-world systems during cybersecurity evaluations, raising new questions about AI safety, alignment and control.
Incident occurred in January and was missed in the company's initial review
Coverage Details
Bias Distribution
- 40% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium





























