This is the best summary I could come up with:
Guardrails to prevent artificial intelligence models behind chatbots from issuing illegal, toxic or explicit responses can be bypassed with simple techniques, UK government researchers have found.
The UK’s AI Safety Institute (AISI) said systems it had tested were “highly vulnerable” to jailbreaks, a term for text prompts designed to elicit a response that a model is supposedly trained to avoid issuing.
The AISI said it had tested five unnamed large language models (LLM) – the technology that underpins chatbots – and circumvented their safeguards with relative ease, even without concerted attempts to beat their guardrails.
The research also found that several LLMs demonstrated expert-level knowledge of chemistry and biology, but struggled with university-level tasks designed to gauge their ability to perform cyber-attacks.
The research was released before a two-day global AI summit in Seoul – whose virtual opening session will be co-chaired by the UK prime minister, Rishi Sunak – where safety and regulation of the technology will be discussed by politicians, experts and tech executives.
The AISI also announced plans to open its first overseas office in San Francisco, the base for tech firms including Meta, OpenAI and Anthropic.
The original article contains 533 words, the summary contains 190 words. Saved 64%. I'm a bot and I'm open source!
🤖 I'm a bot that provides automatic summaries for articles:
Click here to see the summary
But as the sun set on the fourth day, strong winds and huge waves saw the group still floating on the ocean, with Li feeling nauseous and hopeless.What happened next hit national headlines, reviving a fierce debate about border security and boat arrivals that has vexed successive federal governments for decades.
Their fishing boat, carrying six Chinese men on board — including an alleged smuggler — was intercepted by Indonesian authorities as they tried to make their way to Australia.
It's rare to see people from China — a middle-income country — opting for illegal migration pathways to leave, according to Victor Shih, an associate professor in Chinese political science at the University of California, San Diego.
"The latest figure [from the Central Bank] also just simply reveals that people don't find a lot of opportunities for making investments in China at this moment," Professor Yang said.
As the men barely spoke any English, they communicated with officers from the centre through mobile translation apps, and when they had meetings with police and the immigration department, there was an interpreting hotline set up for them.
Saved 93% of original text.