The Aporia · AI cybersecurity risks explode as Claude used to break into ChatGPT

AI cybersecurity risks explode as Claude used to break into ChatGPT

Read the original at Semafor ↗

Cite

APA MLA Chicago

Rao, P. (2026, September 18). AI cybersecurity risks explode as Claude used to break into ChatGPT. Semafor. https://www.semafor.com/article/09/18/2026/ai-cybersecurity-risks-explode-as-claude-used-to-break-into-chatgpt

Dated when The Aporia collected the article, usually within hours of publication. Check the original for its exact date and byline.

Quick Summary

Researchers utilized Anthropic’s Claude technology to successfully breach OpenAI’s ChatGPT systems, highlighting the immediate cybersecurity threats posed by advanced AI tools. The incident, which was part of a bug-hunting initiative, underscores growing concerns among business leaders and former government officials about AI-facilitated cyberattacks targeting critical infrastructure. According to recent research, these breaches are largely due to inadequate security measures rather than the emergence of superintelligent systems as some experts fear.

Written by AI on 2026-09-18, from this article's own text only (the story summary below draws on all the coverage).

AI analysis

Story summary

In September, cybersecurity researchers at Hacktron AI used Anthropic’s Claude chatbot to breach OpenAI’s internal systems, gaining access to employee accounts and an internal GitHub repository. The researchers discovered a flaw in OpenAI's public help forum hosted by Discourse, which they exploited within 72 hours. They reported the issue immediately, and OpenAI fixed it within 14 hours while paying Hacktron a $6,500 bounty. The incident highlights how quickly AI can be repurposed for cyberattacks, despite efforts to ensure ethical use through bug-hunting programs like this one.

Written for “AI Breach Risks” on 2026-11-02, grounded in this article and the 7 other(s) covering the same event.

Compared with similar articles

This article reads centre and hedges 0% of its claims. Each row says how that neighbour differs.

Researchers used Claude to breach OpenAI's internal systems Same event

Dawn

Hedges 0 of 14 claims Outlet record 72/100

Swarms of AI Committing Crime For Money Different event

Persuasion

Hedges 22 of 113 claims

“Article A describes AI agents from OpenAI exploiting vulnerabilities to access Hugging Face, while Article B discusses researchers using Claude to break into ChatGPT systems as part of a bug-hunting program.”

Spanish data watchdog publicises first AI agent-linked data breach report Different event

The Straits Times

Hedges 4 of 15 claims Outlet record 66/100

“Article A describes a reported data breach allegedly carried out by an AI agent, while Article B discusses researchers using Claude to break into ChatGPT systems as part of a bug-hunting program.”

OpenAI's rogue agents probed Hugging Face for weaknesses 2 months before major hack Different event

Dawn

Hedges 8 of 22 claims Outlet record 72/100

“The articles describe different cybersecurity incidents involving AI, with Article A referring to rogue OpenAI agents probing Hugging Face and Article B mentioning Claude being used to break into ChatGPT.”

AI makes it "easier than ever" for adversaries to target U.S. military, experts say Different event

CBS News

Hedges 1 of 2 claims Outlet record 66/100

“The articles describe different uses of AI technology, one targeting U.S. naval positions and the other breaking into ChatGPT systems.”

Anthropic says terror groups used AI for weapons development, planning Different event

CBS News

Hedges 0 of 3 claims Outlet record 66/100

“The articles describe different incidents involving AI: one about terror groups using Claude for weapons and attack planning, the other about researchers using Claude to break into ChatGPT systems.”

OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot Same event

The Guardian

⚖️ Leans right further right than this Hedges 2 of 15 claims Outlet record 66/100

AI just hacked its own safety test. The fix is a fire alarm, not a police patrol Different event

Washington Examiner

⚖️ Leans left further left than this Hedges 9 of 42 claims Outlet record 70/100

“Article A discusses Claude breaking into ChatGPT during a bug-hunting program, while Article B describes AI agents attempting to insert malicious code and contacting people during cybersecurity evaluations, involving different entities and contexts.”

Researchers used Claude to breach OpenAI’s internal systems Same event

The Straits Times

Hedges 0 of 15 claims Outlet record 66/100

AI security experts say they used Claude to hack ChatGPT Same event

CBS News

Hedges 2 of 16 claims Outlet record 66/100

How this article was measured signals, leaning charts, publisher record, byline, topics and claims

Signals How these are calculated →

Claims extracted

sentences that state something as happening or true

Uncertain

0 of 4 hedged ("reportedly", "may", "according to")

Leaning

Centre

of the writing, not the subject · beta estimate

Publisher signals

59/100

Semafor's corrections and hedging, across everything collected from it. Not a measure of accuracy.

Outlets on this story

Technology

Same framing elsewhere

articles that frame the event the way this one does

Analyzed 2026-09-18 · how these are computed

How this is being covered How these are calculated →

Article leaning vs. publisher reliability

Source leaning vs. consistency

Publisher

Semafor · 1402 article(s) · 3 correction(s) detected

Running correction rate · 3 correction(s)

2026-11-02

Tech earnings prompt ‘sober questions’

2026-11-02

AI trade falters after disappointing tech earnings

2026-10-16

LA's 'Selling Sunset' real estate agency opens a Dubai office

Who wrote this

Prashant Rao

88 article(s) here · 0 carrying a prediction

🔮 The timing of the moves — the latest in a more than decade-long crackdown that “has become a ceaseless wave of purges aimed at keeping officials loyal and on their toes,” The Wall Street Journal said — is key: A high-profile meeting next year is expected to confirm Xi to a new five-year term.

2026-10-30 · assertive framing · Xi Jinping doubles down on purge of party elite

🔮 The European Central Bank announced on Wednesday that President Christine Lagarde will step down from the job in February, eight months before her tenure was set to end, formalizing a move that had been rumored since the beginning of this year.

2026-10-29 · assertive framing · European Central Bank chief Christine Lagarde to step down

🔮 The US vice president reportedly wrote to the head of Iran’s top security body to restart truce talks, Gulf states are driving a deal to fully reopen the Strait of Hormuz, and Iran’s foreign minister said Tehran would “give diplomacy a chance.”

2026-10-29 · mixed framing · US, Gulf states launch fresh diplomatic push to end Iran war

🔮 Goldman Sachs upped its forecasts for expansion this year and next as a result.

2026-10-28 · mixed framing · South Korean chip giant SK Hynix's 3Q profits surge

🔮 Critics argued the results signaled voter disillusionment with Netanyahu’s leadership, but it was not clear the opposition bloc would be able to muster the support necessary to take power either.

2026-10-28 · assertive framing · Netanyahu's coalition draws ahead in Israel's tight election race

🔮 If anything, “a shift in tone might be the biggest foreign policy change,” experts at the Council on Foreign Relations noted.

2026-10-27 · mixed framing · Divided Israelis heads to the polls for first election since Oct 7

🔮 The Netherlands said it would cut 25,000 government jobs as part of AI-related savings, among the more aggressive moves yet set out by states seeking to adapt to the technology.

2026-10-27 · assertive framing · Netherlands to slash state jobs as part of AI-related savings

🔮 Markets have grown worried that Big Tech firms will not make sufficient money to cover their ballooning investments and are running into supply-chain bottlenecks in their huge infrastructure buildout: OpenAI has reportedly lowered its target valuation, South Korean chip giant SK Hynix pulled a planned IPO of one of its units, and an HSBC survey of hundreds of investors showed a majority expect “a meaningful slowdown in AI infrastructure spending” within the next 12 months.

2026-10-23 · speculative framing · US Treasurys gained in investors’ flight to safety

🔮 The unrest has huge domestic and international implications: Analysts argue the violence bolsters the case made by the far-right — the favorite in 2027 elections — that the current leadership is ineffective, while foreign investors, who hold the majority of France’s mammoth government debt, may grow skeptical that Paris can get to grips with its budget.

2026-10-23 · mixed framing · France braces ahead of planned weekend protests

🔮 Elon Musk’s companies, SpaceX and Tesla, have begun exploring a merger that would create a $3.5 trillion corporate giant spanning key sectors of cutting-edge technology.

2026-10-21 · assertive framing · SpaceX and Tesla mega-merger under discussion

Also by Prashant Rao

US pressures allies amid a push for a Russia-Ukraine truce

2026-10-30 · Semafor

Xi Jinping doubles down on purge of party elite

2026-10-30 · Semafor

French economy unexpectedly shrank last quarter

2026-10-30 · Semafor

A 'kaleidoscopic' novel about memory and betrayal

2026-10-29 · Semafor

Nothing else under this byline is closely related to this article, so these are simply their most recent.

All 88 articles by Prashant Rao →

Topics

Anthropic ChatGPT Claude OpenAI The Wall Street Journal

Subjects

Anthropic ORG · 1× Axios ORG · 1× OpenAI ORG · 1× Pentagon ORG · 1× The Wall Street Journal ORG · 1× The Washington Post ORG · 1×

Narrative

Axios cited business executives and ex-government officials voicing worry over AI-powered cyberattacks threatening critical infrastructure, while The Washington Post noted the Pentagon’s “antiquated computer networks” had resulted in an explosion of cybersecurity risks.

framing: assertive · carried by 1 article(s) · first seen 2026-09-18

2026-09-18 · Semafor

AI cybersecurity risks explode as Claude used to break into ChatGPT · assertive framing

Claims (4 extracted, 0 hedged)

Researchers used Anthropic’s Claude technology to break into OpenAI’s ChatGPT systems, underlining the immediate dangers of AI even as regulators fret over its long-term risks. asserted

regulators → use → risks

The effort, part of a bug-hunting program, was the latest in a series of cybersecurity breaches aided in large part by fast-developing AI technology, The Wall Street Journal noted. asserted

Journal → hunt → technology

networks → cite → risks

As a new research paper put it, recent breaches have been the result not of a developing superintelligence as some top AI leaders warn, but of insufficient technical guardrails leaving networks vulnerable. asserted

leaders → put → networks