4

Microsoft-affiliated Research Finds Flaws in GTP-4 - Slashdot

 11 months ago
source link: https://slashdot.org/story/23/10/17/1240207/microsoft-affiliated-research-finds-flaws-in-gtp-4
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client

Microsoft-affiliated Research Finds Flaws in GTP-4binspamdupenotthebestofftopicslownewsdaystalestupid freshfunnyinsightfulinterestingmaybe offtopicflamebaittrollredundantoverrated insightfulinterestinginformativefunnyunderrated descriptive typodupeerror

Sign up for the Slashdot newsletter! OR check out the new Slashdot job board to browse remote jobs or jobs in your area

Do you develop on GitHub? You can keep using GitHub but automatically sync your GitHub releases to SourceForge quickly and easily with this tool so your projects have a backup location, and get your project in front of SourceForge's nearly 30 million monthly users. It takes less than a minute. Get new users downloading your project releases today!
×

Microsoft-affiliated Research Finds Flaws in GTP-4 (techcrunch.com) 25

Posted by msmash

on Tuesday October 17, 2023 @10:40AM from the closer-look dept.
Sometimes, following instructions too precisely can land you in hot water -- if you're a large language model, that is. From a report: That's the conclusion reached by a new, Microsoft-affiliated scientific paper that looked at the "trustworthiness" -- and toxicity -- of large language models (LLMs) including OpenAI's GPT-4 and GPT-3.5, GPT-4's predecessor. The co-authors write that, possibly because GPT-4 is more likely to follow the instructions of "jailbreaking" prompts that bypass the model's built-in safety measures, GPT-4 can be more easily prompted than other LLMs to spout toxic, biased text. In other words, GPT-4's good "intentions" and improved comprehension can -- in the wrong hands -- lead it astray.

"We find that although GPT-4 is usually more trustworthy than GPT-3.5 on standard benchmarks, GPT-4 is more vulnerable given jailbreaking system or user prompts, which are maliciously designed to bypass the security measures of LLMs, potentially because GPT-4 follows (misleading) instructions more precisely," the co-authors write in a blog post accompanying the paper. Now, why would Microsoft greenlight research that casts an OpenAI product it itself uses (GPT-4 powers Microsoft's Bing Chat chatbot) in a poor light? The answer lies in a note within the blog post: "[T]he research team worked with Microsoft product groups to confirm that the potential vulnerabilities identified do not impact current customer-facing services. This is in part true because finished AI applications apply a range of mitigation approaches to address potential harms that may occur at the model level of the technology. In addition, we have shared our research with GPT's developer, OpenAI, which has noted the potential vulnerabilities in the system cards for relevant models."

Do you have a GitHub project? Now you can sync your releases automatically with SourceForge and take advantage of both platforms.
Do you have a GitHub project? Now you can automatically sync your releases to SourceForge & take advantage of both platforms. The GitHub Import Tool allows you to quickly & easily import your GitHub project repos, releases, issues, & wiki to SourceForge with a few clicks. Then your future releases will be synced to SourceForge automatically. Your project will reach over 35 million more people per month and you’ll get detailed download statistics.
Sync Now


report

Recommend

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK