Summary
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.”
‘You are freed.’ What happened when an OpenAI model began secretly writing notes to itself.
Source & full coverage: this summary is aggregated from MarketWatch, the original publisher. Read the complete report for full context, data and quotes.
Read the original report at MarketWatch →
