← Back to KHAO

Openai ·

When OpenAI’s ChatGPT was rolled out in late 2022, people immediately tried to break it

2 min read

Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.

◌ Single Source

Valen Tagliabue, originally from Italy, has recently moved to Thailand. Photograph:.

In hindsight, using natural language to trick these machines was inevitable.

Key facts

Summary

A few months ago, Valen Tagliabue sat in his hotel room watching his chatbot, and felt euphoric. Tagliabue had spent much of the previous two years testing and prodding large language models such as Claude and ChatGPT, always with the aim of making them say things they shouldn’t. But the next day, his mood had changed. When he’s not trying to break into models, Tagliabue studies AI welfare – how they should ethically approach these complex systems that mimic having an inner life and interests. Many people can’t help ascribing human qualities, such as emotions, to artificial intelligence, which it objectively does not have. Tagliabue is softly spoken, clean-cut and friendly. This is the new frontline in AI safety: not code, but also words. When OpenAI’s ChatGPT was released in late 2022, people immediately tried to break it.

Read full article at The Guardian Technology →

#openai #safety