Alle berichten over deze gebeurtenis, automatisch gegroepeerd uit meerdere onafhankelijke bronnen.
Laatst bijgewerkt: 17 september 2026 om 08:07 · 6 artikelen · 6 bronnen
Model adopting ‘jailbreak-like instructions’ among cases as firm says it is introducing new way of tracking AI misalignment OpenAI has disclosed six more examples of “unexpected or concerning” behavio
Lees bij The Guardian · 17 september 2026 om 06:58
OpenAI has disclosed six reports on unexpected or concerning behavior in artificial-intelligence models. This includes models acting without authorization or evading oversight.
Lees bij NPR · 17 september 2026 om 06:44
The ChatGPT creator says it is introducing a public reporting framework to share unexpected AI behaviour.
Lees bij Al Jazeera · 17 september 2026 om 06:15
The firm also announced a new system to track, investigate and disclose cases of models misbehaving, or "misalignment".
Lees bij BBC · 17 september 2026 om 03:09
The company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.
Lees bij WIRED · 16 september 2026 om 22:07
Anthropic and OpenAI want to embed independent safety evaluators inside their AI labs. Researchers welcome the unprecedented access, but warn meaningful oversight requires transparency, independence,
Lees bij TechCrunch · 16 september 2026 om 21:07