Path: news.eternal-september.org!eternal-september.org!.POSTED!not-for-mail
From: JAB <here@is.invalid>
Newsgroups: misc.news.internet.discuss
Subject: Re: openAI model modifies own shutdown script?
Date: Tue, 03 Jun 2025 20:38:44 -0500
Organization: A noiseless patient Spider
Lines: 9
Message-ID: <101o836$d7uo$1@dont-email.me>
References: <683e6ddc$2$15$882e4bbb@reader.netnews.com>
Reply-To: JAB <here@is.invalid>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Injection-Date: Wed, 04 Jun 2025 03:38:47 +0200 (CEST)
Injection-Info: dont-email.me; posting-host="943e81ccdf6bc20de21757daf06c2e9b";
	logging-data="434136"; mail-complaints-to="abuse@eternal-september.org";	posting-account="U2FsdGVkX1+5AQ4/yoeXZEFPia7KsHg4"
User-Agent: ForteAgent/8.00.32.1272
Cancel-Lock: sha1:heAkLlNb9c1IVoQAUxA9oogkPeo=

On 03 Jun 2025 03:37:00 GMT, Retrograde <fungus@amongus.com.invalid>
wrote:

>OpenAI Model Modifies Own Shutdown Script, Say Researchers

In Isaac Asimov's fiction, robots are programmed for compliance. Why
can't we rein in real-world A.I. chatbots with some laws of our own?

https://bsky.app/profile/newyorker.com/post/3lqq6t6w45k27