AI cybersecurity risks explode as Claude used to break into ChatGPT

Read the original at Semafor ↗
Semafor · collected 2026-09-18 · by Prashant Rao

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 locally by qwen2.5:14b on 2026-09-18, using this article's own text rather than the other coverage of the same event (that is the story summary below).

AI analysis runs on qwen2.5:14b, locally

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 2026-10-05, grounded in this article and the 7 other(s) covering the same event.

Signals How these are calculated →

Claims extracted
4
claim-shaped sentences
Uncertain
0%
0 of 4 hedged
Leaning
Centre
of the writing, not the subject · beta estimate
Correction & hedging signals
94.9
corrections and hedging in what we collected; not a measure of accuracy
Outlets on this story
8
Technology
Narrative spread
1
articles carrying this framing
Analyzed 2026-09-18 · how these are computed

Story

📰 AI Breach Risks
Technology · 8 article(s) covering the same event. See how they differ ↓

How this is being covered How these are calculated →

Article leaning vs. publisher reliability
Source leaning vs. consistency

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 · 100%
Dawn
⚖️ leaning not scored 🔴 0% hedged 0 of 14 📰 publisher trust 77
“Both articles describe the identical incident of researchers using Anthropic's Claude technology to break into OpenAI’s ChatGPT systems on the same date.”
Swarms of AI Committing Crime For Money different event · 95%
Persuasion
⚖️ leaning not scored 🔴 19% hedged 22 of 113
“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 · 95%
The Straits Times
⚖️ leaning not scored 🔴 27% hedged 4 of 15 📰 publisher trust 59
“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 · 95%
Dawn
⚖️ leaning not scored 🔴 36% hedged 8 of 22 📰 publisher trust 77
“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 · 95%
CBS News
⚖️ leaning not scored 🔴 50% hedged 1 of 2 📰 publisher trust 66
“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 · 95%
CBS News
⚖️ leaning not scored 🔴 0% hedged 0 of 3 📰 publisher trust 66
“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 · 95%
The Guardian
⚖️ Leans right further right than this 🔴 13% hedged 2 of 15 📰 publisher trust 68
“Both articles describe researchers using Anthropic's Claude AI to hack into OpenAI’s ChatGPT systems on the same date.”
AI just hacked its own safety test. The fix is a fire alarm, not a police patrol different event · 95%
Washington Examiner
⚖️ Leans left further left than this 🔴 21% hedged 9 of 42 📰 publisher trust 72
“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 · 95%
The Straits Times
⚖️ leaning not scored 🔴 0% hedged 0 of 15 📰 publisher trust 59
“Both articles describe researchers using Anthropic’s Claude AI to break into OpenAI's systems on the same day, September 18, 2026.”
AI security experts say they used Claude to hack ChatGPT same event · 95%
CBS News
⚖️ leaning not scored 🔴 12% hedged 2 of 16 📰 publisher trust 66
“Both articles describe the same incident where researchers used Anthropic’s Claude technology to hack into ChatGPT, with details about accessing an employee's account and retrieving source code information.”

Publisher

Semafor · 751 article(s) · 0 correction(s) detected
No corrections detected for this publisher. That may mean careful reporting, or simply that nothing has been checked.

Who wrote this

Prashant Rao
50 article(s) here · 0 carrying a prediction
🔮 Economists were also worried about French levels of borrowing, with Paris set to unveil a draft budget today that aims to close a yawning deficit and will likely be politically divisive; France this week announced plans for record bond sales, despite the country’s rising debt-to-GDP ratio.
2026-10-01 · assertive framing · Global bond rout gathers pace as debt fears grow
🔮 US President Donald Trump is set to kick off a month of campaigning, though GOP candidates in tough battles have distanced themselves from a historically unpopular leader.
2026-10-01 · assertive framing · US midterms race on a knife's edge
🔮 OpenAI reportedly aims to raise $30 billion in a new funding round valuing the company at $1.4 trillion, underlining how what was set to be a bumper IPO market to end the year is stalling.
2026-09-30 · mixed framing · OpenAI hopes to raise $30B in new funding round
🔮 Paris — already grappling with debt equivalent to 119% of GDP — said it would sell a record amount of bonds next year, prompting the spread between French government bonds and their German equivalents to widen, reflecting what investors see as a rising risk premium.
2026-09-30 · assertive framing · France plans record bond sale as debt fears grow
🔮 European countries have hardened their stance against Chinese imports over fears that an influx of goods like solar panels and EVs could hollow out the bloc’s industries.
2026-09-29 · mixed framing · Brussels trains ‘trade bazooka’ at Beijing
🔮 US President Donald Trump rejected a peace proposal from Iran on Friday; he told Axios he believed talks would resume this week, though The Wall Street Journal reported that he told aides he expects to bomb Iran again after November’s midterms.
2026-09-28 · assertive framing · Oil prices rise as hope for a US-Iran truce fades
🔮 US President Donald Trump and Chinese leader Xi Jinping were set to conclude a superpower summit that was long on ceremony and short on substance.
2026-09-25 · assertive framing · Trump and Xi conclude Washington visit that was short on substance
🔮 Officials where the facility is being built have delayed permits necessary to power the project, and Oracle may seek to delay lease payments.
2026-09-25 · mixed framing · Oracle force majeure on US data center showcases AI infrastructure risks
🔮 The heads of Anthropic and OpenAI will brief the UN Security Council today, as their calls for a slowdown in development compete with the interests of superpowers more concerned with winning the AI race.
2026-09-23 · assertive framing · Anthropic and OpenAI bosses to address the UN
🔮 To make matters worse, a second inflationary shock could be in the works, The Wall Street Journal’s chief economics commentator warned, which means interest rates could remain high for longer than expected.
2026-09-23 · mixed framing · Leaders scramble to curb rising fuel prices
Also by Prashant Rao
Asian giants face looming graduate job crisis
2026-10-01 · Semafor
Global bond rout gathers pace as debt fears grow
2026-10-01 · Semafor
US midterms race on a knife's edge
2026-10-01 · Semafor
OpenAI hopes to raise $30B in new funding round
2026-09-30 · Semafor
Nothing else under this byline is closely related to this article, so these are simply their most recent.
All 50 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
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. asserted
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
💬Give feedback
🕘History 🎫Support
Terms · Privacy · beta v2.0.0
Articles to 5 Oct 2026