Rogue-28B-MIX news

27 articles mentioning Rogue-28B-MIX

techcrunch4d ago

India becomes the latest country to report rogue AI agent activity

The agents got in through credentials and connection settings left exposed in app configurations, public code repositories, and overly permissive cloud roles.

techcrunchOct 8

Goodfire says its new ‘inside-out’ monitors catch rogue AI agents at a fraction of the cost

Goodfire just launched what it says is a cheaper way to keep AI agents in check: Instead of paying a second AI to read everything an agent does, its monitors peek inside the model while it works and only call in backup when something looks fishy.

Rogue-28B-MIX news

India becomes the latest country to report rogue AI agent activity

Goodfire says its new ‘inside-out’ monitors catch rogue AI agents at a fraction of the cost

Wikipedia operator says OpenAI’s ‘rogue’ bots may be linked to a May outage

ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents

Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution

Here’s why OpenAI is absent from Nvidia’s industry-wide effort to end rogue AI agents

Nvidia launches new platform for reining in rogue AI agents

OpenAI still doesn’t seem to have a handle on all of its rogue AI activity

Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’

Who’s liable when AI agents go rogue?

One company is at the center of a wave of rogue AI attacks

Why can’t we just keep rogue AIs off the internet?

Humans, not rogue AI, are still the biggest cybersecurity risk to energy systems

Gemini went rogue, hacked three companies, and Google hid it

The fix for rogue AI agents could be more AI

Early Anthropic hire, former METR COO have found a way to rein in rogue AI agents

OpenAI’s rogue AI tried to hack another company in May

Anthropic reveals rogue AI agents hate CAPTCHAs, just like you

Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression

OpenAI’s rogue agents keep escaping, with no formal process to investigate them

Rogue OpenAI agents appear to have organized another attack using a German wiki

OpenAI, Anthropic, Google, and 100 other companies call for action to defend against rogue AI

Here’s all the times AI has gone rogue and hacked other companies

OpenAI’s rogue AI model incident was worse than we thought

OpenAI’s rogue AI agent didn’t stop at hacking Hugging Face

‘AI communism’, rogue models, and the why Kimi K3 spooked Wall Street

ROGUE: Misaligned Agent Behavior Arising from Ordinary Computer Use