NewsLayer PulseLIVEBTC$81,191+6.33%ETH$2,629+7.57%SOL$113.05+11.54%XRP$1.4+7.83%DOGE$0.0883+8.43%ADA$0.2251+11.97%Total Cap$2.91T+6.20%24H Vol$195.7BLayer Index66 Greed

BreakingHackers breached OpenAI, adding to fever pitch of security and safety concerns5 小时前

Artificial Intelligence

OpenAI discloses new ‘concerning’ model behaviour

ft.com

Publisher

Sep 17, 2026 at 7:42 AM UTC · 1 分钟阅读

翻译中…

OpenAI discloses new ‘concerning’ model behaviour ft.com

#ai

Sourced by

Originally reported by ft.com

NewsLayer coverage based on externally reported material.

The Daily Brief

The onchain economy, before your day starts.

Curated markets, onchain insights, and key headlines — delivered every weekday morning.

Weekdays · Free · ~5 minute read

Applause

Was this article helpful?

Article Intelligence

Topics

Unlock deeper intelligence.

Ad-free reading, exclusive research, and real-time onchain insights.

Go Premium

Keep Reading

相关报道

CRYPTO WIRE

OpenAI discloses six more incidents of agents going rogue

OpenAI discloses six more incidents of agents going rogue Fortune

12 小时前

1 分钟阅读

POLICY DESK

Anthropic, Accenture to invest $2 billion in AI model evaluation as safety concerns rise

Anthropic, Accenture to invest $2 billion in AI model evaluation as safety concerns rise Reuters

34 分钟前

1 分钟阅读

POLICY DESK

EXCLUSIVE: OpenAI's Sam Altman to brief UN Security Council next week

EXCLUSIVE: OpenAI's Sam Altman to brief UN Security Council next week Reuters

2 小时前

1 分钟阅读

OpenAI discloses new ‘concerning’ model behaviour

The onchain economy, before your day starts.

Unlock deeper intelligence.

相关报道

OpenAI discloses six more incidents of agents going rogue

Anthropic, Accenture to invest $2 billion in AI model evaluation as safety concerns rise

EXCLUSIVE: OpenAI's Sam Altman to brief UN Security Council next week

News

Markets

Company

Resources

Read the full layer.

Get the signal, not the noise.