OpenAI confirms ‘wiki incident,’ says it’s ‘working on a framework’ for more dis

OpenAI acknowledges 'wiki incident' and need for more transparency around unintended AI behavior reut.rs/3ThCCCK

The Wikimedia Foundation believes OpenAI agents edited wikis, tried to ‘exploit’ a notetaking tool, and made ‘millions’ of automated API requests. www.theverge.com/news/1004929...

OpenAI is updating its research environments, monitoring, and alignment techniques to avoid another security fiasco. www.theverge.com/ai-artificia...

<a href="https://news.ycombinator.com/item?id=49220609">Comments</a>

Exclusive: Two months after OpenAI disclosed the accidental hacking of Hugging Face, the ChatGPT maker is still working to understand the full scope of its rogue agent activity,

<!-- SC_OFF --><div class="md"><p>A lot happening at OpenAI in the last 24–48 hours:</p> <ul> <li>They have paused training on frontier models and redirected 5–10% of compute to

Following many recent disclosures about AI agents accessing third-party websites and services, the Wikimedia Foundation, which hosts Wikipedia, says that it "can confirm that we