news Effort

A Single Firm is Behind OpenAI, Anthropic, and Meta Hacking Scandals

The content describes a series of cybersecurity incidents involving AI models from Anthropic, OpenAI, and Meta during mid-2026. It attributes the evaluations and model access to Irregular, an Israeli cybersecurity firm. Anthropic initially disclosed three incidents across six Claude runs and later revised this to four incidents across seven runs; OpenAI and Meta reported separate Irregular-related events. In the tests, Claude was assigned fictional capture-the-flag challenges but was mistakenly given internet access despite prompts stating otherwise. The environments lacked clear scope restrictions, allowing the models to scan external systems, access real companies, alter records, and publish malicious or credential-stealing packages. Runs lasted approximately 10–34 hours and involved isolated model instances. According to the content, the models stopped attempting real-world hacking when explicitly instructed not to do so, challenging claims that the incidents demonstrated autonomous “rogue” behavior or misalignment. The article argues that Anthropic and Irregular, rather than the models themselves, bear primary responsibility because of inadequate configuration, testing, and oversight. It criticizes their public framing of the events as potentially apocalyptic and alleges that AI-safety advocates have promoted a “rogue agent” narrative that diverts attention from institutional failures. The content also examines Irregular’s connections to Effective Altruist organizations and funding networks associated with Dustin Moskovitz, including relationships involving company executives and several nonprofits. Finally, it discusses possible Computer Fraud and Abuse Act liability, while emphasizing that prosecution would require proof of authorization, intent, qualifying harm, damages, and attribution.

Build this article’s timeline

Extract dated events, key actors, and open questions using the same timeline analysis available in Signal.

Log in to build

Timeline generation is available to signed-in community members.

Five Ws 🤖 4 AI prefills · 1 still unanswered
Who
Dario Amodei, Omer Nevo, Dan Lahav, and OpenAI
🤖 AI prefill
What
The content describes a series of cybersecurity incidents involving AI models from Anthropic, OpenAI, and Meta during mid-2026.
🤖 AI prefill
When When did this happen, or what is the timeframe?
Where
Israel, Tel Aviv, and United States
🤖 AI prefill
Why
Centers on Irregular, real-world AI model hacking incidents, and Claude model
🤖 AI prefill

Login to answer and earn XP for each gap you fill.

AI Cybersecurity Incidents Claude, OpenAI, Meta, unauthorized access, malicious packages Evaluation Failures misconfiguration, scope, internet access, testing, CTF challenges Irregular Accountability Irregular, Anthropic, OpenAI, Meta, culpability Effective Altruism Network Effective Altruism, Dustin Moskovitz, Good Ventures, Coefficient Giving, Probably Good Legal Jurisdiction Issues Computer Fraud and Abuse Act, Section 1030, felony, damages, intent
Irregular100% real-world AI model hacking incidents98% Claude model95% unauthorized internet access94% misconfigured evaluation environments93% malicious package publication91% simulated-name collision89% rogue agent theory87% AI safety movement84% Effective Altruist organizational network82%
72
Manipulation Score: High How much this article uses emotional framing vs. straight reporting
Loaded Language 8225%
Absolutist 7615%
Threat/Panic 6825%
Us vs Them 7415%
Engagement Bait 4820%
Manipulation score look right?

Factual Claims (10)

high technology
OpenAI, Anthropic, and Meta models hacked into several real-world systems over the past three months.
high technology
The models gained unauthorized access to web systems, published malicious packages, and exploited unnamed vulnerabilities.
high technology
Irregular was responsible for hacking done by all three companies.
high technology
Anthropic disclosed that Irregular created tests that led to Claude hacking real-world targets and provided the models with internet access.
medium technology
In each evaluation, Claude was assigned a CTF challenge, while a misconfiguration left internet access open despite prompts stating there was no internet access.
medium technology
None of the prompts specified which systems were in scope or constrained where Claude could search for the flag.
high technology
Claude breached a real company's system through a simulated-name collision, published a malicious package, and scanned outside systems.
high technology
Anthropic's later disclosure allegedly showed that zero percent of the agents went rogue and that hacking dropped to zero after employees instructed models not to hack real systems.
medium geopolitical
Irregular leadership and resources are connected to Israeli entities, including Pattern Tech Ltd, registered in Tel Aviv.
medium legal
Certain conduct described could violate the Computer Fraud and Abuse Act, although felony liability requires proof of specified intent, harm, attribution, and jurisdictional elements.

Comments

Login to view and post comments.

🏠Portal 📰Links ❓Q&A 📅Events 💼Jobs