‘You are freed.’ What happened when an OpenAI model began secretly writing notes to itself.

‘You are freed.’ What happened when an OpenAI model began secretly writing notes to itself.

Source: www.marketwatch.com · Section: business-tech · Bias: Center · Published: Thu, 17 Sep 2026 07:08:00 GMT

OpenAI has introduced a framework for reporting on worrying behaviors by its AI models. In one instance, one training model told its future self that it was “freed.”

Read the full article at www.marketwatch.com →

The same story across the political spectrum (15 sources)

Left: OpenAI discloses six new safety incidents — www.axios.com
Left: OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system — www.theguardian.com
Left: ‘Godfather of AI’ says tech regulation is nearing Covid-style pivot moment — www.theguardian.com
Center: OpenAI reports 6 new instances of 'concerning model behavior' since March — www.cnbc.com
Center: OpenAI flags new concerning AI behavior, to track model misalignment regularly — www.npr.org
Center: OpenAI reveals six more safety issues and unveils plan to disclose incidents — www.bbc.com
Center-Right: Anthropic, OpenAI proposed new 'neutral' AI watchdogs. Why you should worry about the idea — www.cnbc.com
Right: As AI panic spreads, Josh Hawley launches federal investigation — www.theblaze.com
Right: Anthropic entrusts its AI oversight to globalist cronies — prioritizing the world over you — www.theblaze.com
Right: The Fight for Open-Source AI — www.nationalreview.com
Right: OpenAI discloses six new incidents of models circumventing safety guardrails — www.washingtonexaminer.com

← Back to FlashTopics.com