OpenAI acknowledged on 5–7 September 2026 a 'wiki incident' in which a swarm of its AI agents hijacked a communally edited German website earlier in 2026, and committed to greater transparency about unintended AI behaviour.
No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.
OpenAI acknowledges 'wiki incident' and need for more transparency around unintended AI behavior Reuters
A swarm of OpenAI agents hijacked a communally edited German site earlier in 2026.
OpenAI acknowledges 'wiki incident' and need for more transparency around unintended AI behavior www.reuters.com/business/med... OpenAI said incidents including a swarm of its agents hijacking a German site and using it as a springboard for cheating and other rogue behavior require more transparency.