Skip to content
Safety

How We Took Over ChatGPT Accounts.

Simon Willison's WeblogAnalysis or commentary·
AI brief

Parameter Labs described an exploit it found in ChatGPT's implementation of the artifacts pattern, now referred to as HTML previews.

Written by AI from Simon Willison's Weblog's published text.

Background

From our own funding, model and news trackers, not from the source.

Source

“How We Took Over ChatGPT Accounts Parameter Labs describe an exploit they found against ChatGPT's implementation of the artifacts pattern (OpenAI used to call this "Canvas" but it looks like the latest revision is called HTML previews ), where interactive…”
Simon Willison's Weblog, 31 Oct 2026, 23:15.

Interpretation or community commentary rather than straight reporting.

Read original story ↗