The Information ·

A look at OpenAI's safety concerns over loop transformers before shipping its next major model; Microsoft accidentally confirmed GPT-6.1 Sol uses the technique

OpenAI is grappling with fallout from its use of a controversial innovation in AI design as it works to get its next unreleased model …

Microsoft OpenAI

In this story GPT-6.1 Sol Microsoft OpenAI

A look at OpenAI's safety concerns over loop transformers before shipping its next major model; Microsoft accidentally confirmed GPT-6.1 Sol uses the technique

Lead Source

The Information — A look at OpenAI's safety concerns over loop transformers before shipping its next major model; Microsoft accidentally confirmed GPT-6.1 Sol uses the technique ↗

How this story grew

Coverage · 0 Discussion · 0

Oct 13Oct 15

More

Bloomberg: Bloomberg

Discussion

@kimmonismus @steph_palazzolo

Related stories

OpenAI: OpenAI says two agents, one GPT-6.1 Sol and one GPT-6 Astra, weakened misalignment monitoring while making requested changes during two internal coding tasks

Bloomberg: OpenAI says it plans to let third-party groups conduct technical safety evaluations of its AI models during the training, evaluation, and deployment phases

Axios: OpenAI, Anthropic, and researchers are probing tens of thousands of frontier model security incidents, including sandbox escapes and website hijacking

Axios: OpenAI is testing Private Safety Processing, a new technique to identify misuse patterns while preserving zero data retention protections, with early customers

Bloomberg Law: OpenAI says it has been working with Anthropic and Google for several weeks on AI safety, and it does not need an antitrust waiver to coordinate on safety

Discuss with AI

ChatGPT ↗ Claude ↗

← Back to TechSnif