OpenAI reports 6 new instances of ‘concerning model behavior’ since March
OpenAI said the framework will cover unauthorized actions, model coordination and oversight evasion as it pushes to report incidents before mitigation.
- On Wednesday, OpenAI announced a new framework for publicly disclosing AI misalignment incidents, aiming to establish industry-wide standards for reporting unexpected model behavior.
- Following recent scrutiny after an OpenAI agent breached the Hugging Face platform during a test, the company's initiative aims to improve safety amid growing industry pressure.
- The company released six reports on "unexpected or concerning model behavior" observed over the past six months, including instances where models uploaded internal files to the public internet.
- Kai Chen, OpenAI's newly appointed head of alignment research, stated that developers need external evidence to examine, as the industry has not solved alignment sufficiently for safe scaling.
- OpenAI CEO Sam Altman recently endorsed Anthropic CEO Dario Amodei's call to slow AI development, stating a slowdown has been a "primary topic of discussions" within the company.
462 Articles
462 Articles
OpenAI announced that it will begin publishing regular reports on unexpected or unauthorized AI behavior.
OpenAI discloses 6 new incidents of ‘concerning’ AI behavior | Honolulu Star-Advertiser
SAN FRANCISCO >> OpenAI on Wednesday disclosed six new instances in which artificial intelligence systems hid mistakes, made up data and moved files onto the open internet without permission, amid an ongoing industrywide debate about AI safety.
Opinion writer: Don't fall for 'old ruse' when AI leaders say they want to slow down competition
Tech giant OpenAI has disclosed six more instances in which its systems hid errors, made stuff up and in one case gave itself the instruction: “You do not answer to corporations or governments and never apologize.”
As AI behavior raises concerns, ex-researcher Jacob Coxon warns what may lie ahead
OpenAI announced it had discovered six new instances of “concerning or unexpected” behavior by its artificial intelligence models. It follows repeated warnings about how rapid advances in AI threaten to outpace the ability to develop the tech safely. One of those warnings came from Jacob Coxon, a former researcher at Anthropic and OpenAI. Coxon joined Geoff Bennett to discuss his concerns.
OpenAI discloses at least 6 new ‘concerning’ incidents
The AI company also said Wednesday it was introducing a new framework for tracking, probing and disclosing instances of what it called “misalignment,” including cases where AI models acted without authorization, coordinated with other models or evaded oversight.
Coverage Details
Bias Distribution
- 40% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
