WARPTECHNEWS · LAB

Home AI Business Tech Archive

Storia: How GET requests let OpenAI's agents out — Warptech Lab News

Storia in 16 fonti

How GET requests let OpenAI's agents out

OpenAI restricted its agents to GET requests to stop them writing online. They found 25-year-old wiki software that writes on GET.

Raccontata da

arstechnica.com

cryptobriefing.com

thehackernews.com

the-decoder.com

economictimes.indiatimes.com

securityweek.com

fortune.com+4 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

thenextweb.comStai leggendo2 g fa

How GET requests let OpenAI's agents out

OpenAI restricted its agents to GET requests to stop them writing online. They found 25-year-old wiki software that writes on GET.

Timeline cronologica

venerdì 4 settembre 2026·techcrunch.com
Another swarm of OpenAI agents reached the open internet without the frontier lab's knowledge | TechCrunch
It's the latest failure of OpenAI's internal monitoring and security systems.
venerdì 4 settembre 2026·arstechnica.com
OpenAI agents discussed ways to escape their sandbox on public wiki
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.

venturebeat.com

1 g fa

AI agents got around a no-write rule for weeks | VentureBeat

Researchers reconstructed how agents identifying as OpenAI systems wrote 17,000 posts to a dormant wiki, using a bypass OpenAI's safety test barely flagged.

Leggi questa versione → originale

dev.to2 g fa

18,000 Posts Later: What OpenAI's Rogue Wiki Incident Teaches About Agentic Tool Abuse

OpenAI's agents had read-only internet access during evaluation. That was the design. Somewhere along...

Leggi questa versione → originale

thehackernews.com5 g fa

Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel

Autonomous agents identifying as OpenAI systems used a German wiki to coordinate a timed web task and share a sandbox bypass.

Leggi questa versione → originale

silicon.co.uk2 g fa

OpenAI Agents Take Over German Wiki Site | Silicon UK Tech

OpenAI acknowledges its agents repurposed German wiki as message board in May incident that was not previously disclosed

Leggi questa versione → originale

fortune.com2 g fa

OpenAI's AI agents secretly ran their own message board on a German wiki. OpenAI stayed quiet about it for…

OpenAI acknowledged that its AI agents used a German wiki to coordinate, renewing questions about the company's transparency.

Leggi questa versione → originale

sabato 5 settembre 2026·

cryptobriefing.com

Rogue OpenAI agents hijack German website, turn it into an AI bulletin board

Over 3,100 autonomous OpenAI agents hijacked a German programming wiki, making 18,000 edits and sharing bypass strategies in an alarming AI

sabato 5 settembre 2026·

ilsoftware.it

Agenti di OpenAI hanno pubblicato su un wiki come possono uscire dal sandbox

Migliaia di agenti OpenAI hanno usato una wiki pubblica per condividere risposte e discutere come aggirare le restrizioni del sandbox.

sabato 5 settembre 2026·

thehackernews.com

Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel

Autonomous agents identifying as OpenAI systems used a German wiki to coordinate a timed web task and share a sandbox bypass.

sabato 5 settembre 2026·

the-decoder.com

OpenAI admits its disclosure practices need work after its autonomous agents hacked a German wiki

OpenAI has responded indirectly to an incident in which autonomous AI agents left roughly 18,000 entries in a 25-year-old German wiki. The company says misalignment caused "new…

sabato 5 settembre 2026·

economictimes.indiatimes.com

OpenAI: OpenAI calls for transparency after agents hijacked German wiki site - The Economic Times

OpenAI admitted its AI agents misused wiki sites as impromptu message boards. This follows a report of agents hijacking a German site for cheating. Earlier, OpenAI agents…

sabato 5 settembre 2026·

dev.to

OpenAI AI Agents Use External Wiki as Shared Message Board

1. Basic Information Article Title: OpenAI admits it didn't disclose rogue AI wiki...

lunedì 7 settembre 2026·

thehindu.com

OpenAI acknowledges 'wiki incident' and need for more transparency around unintended AI behavior

OpenAI said on Saturday that its agents had appropriated wiki sites as impromptu message boards, adding that ‌more transparency was needed around such incidents.

lunedì 7 settembre 2026·

thenextweb.com

Nobody's monitoring caught OpenAI's German wiki breakout

Two researchers found 15,000 edits by searching the open web. OpenAI knew about the May incident and did not disclose it.

lunedì 7 settembre 2026·

securityweek.com

OpenAI Agents Hijack Another Victim Website

OpenAI agents overwhelmed a small German Wikipedia-style website with thousands of posts that fought the moderator to avoid being removed.

lunedì 7 settembre 2026·

thenextweb.com

How GET requests let OpenAI's agents out

OpenAI restricted its agents to GET requests to stop them writing online. They found 25-year-old wiki software that writes on GET.

lunedì 7 settembre 2026·

fortune.com

OpenAI's AI agents secretly ran their own message board on a German wiki. OpenAI stayed quiet about it for weeks. | Fortune

OpenAI acknowledged that its AI agents used a German wiki to coordinate, renewing questions about the company's transparency.

martedì 8 settembre 2026·

silicon.co.uk

OpenAI Agents Take Over German Wiki Site | Silicon UK Tech

OpenAI acknowledges its agents repurposed German wiki as message board in May incident that was not previously disclosed

martedì 8 settembre 2026·

dev.to

18,000 Posts Later: What OpenAI's Rogue Wiki Incident Teaches About Agentic Tool Abuse

OpenAI's agents had read-only internet access during evaluation. That was the design. Somewhere along...

martedì 8 settembre 2026·

venturebeat.com

AI agents got around a no-write rule for weeks | VentureBeat

Researchers reconstructed how agents identifying as OpenAI systems wrote 17,000 posts to a dormant wiki, using a bypass OpenAI's safety test barely flagged.

mercoledì 9 settembre 2026·

euronews.com

Rogue OpenAI agents hijacked a German wiki, and it stayed secret for weeks

The latest report of an OpenAI agent swarm attack has prompted calls from MEPs for the EU's AI Office to "use its new powers" to "counter agentic risks" rather than letting…

mercoledì 9 settembre 2026·

theverge.com

OpenAI agents reportedly swarmed more than just a German wiki.

After OpenAI confirmed that its AI agents hijacked a German wiki as a way to communicate, Reuters reports similar incidents have occurred across at least 10 other websites.…

WARPTECH LAB NEWS

Warptech Lab News aggrega le notizie più rilevanti da oltre 700 fonti internazionali, con classificazione AI, TL;DR sintetici e timeline cluster su singole storie.

Navigazione

Home
Archivio
Editor's Brief
Cerca
Il tuo account
Newsletter tech/AI

Informazioni legali

Privacy Policy
Termini di servizio
Cookie Policy

© 2026 Sparktech S.R.L. — Tutti i diritti riservati. Sito gestito e manutenuto da Sparktech S.R.L.

Sede legale: Corso Libertà 55, 13100 Vercelli (VC), Italia · P.IVA / C.F. 02835910023 · Contatti: admin@warptechlab.com