News for hackers. Stuff that matters.

A comment on ChatGPT agent: bridging research and action. Parent comment

Re:ChatGPT agent: bridging research and action by dustingetz on Thursday July 17, 2025 @07:34PM (#44599516)
98% sure each commit doesn’t corrupt the database, regress a customer feature, open a security vulnerability. 50 commits later … (which is like, one day for an agentic workflow)
[ Parent | on HN ]
Re:ChatGPT agent: bridging research and action by koolba on Thursday July 17, 2025 @08:07PM (#44599756)
It’s only a 64% chance of corruption after 50 such commits at a 98% success.
[ Parent | on HN ]
Re:ChatGPT agent: bridging research and action by arthurcolle on Thursday July 17, 2025 @11:06PM (#44600807)
I would be embarrassed to be at OpenAI releasing this and pretending the last 9 months haven't happened... waxing poetically about "age of agents" - absolutely cringe and pathetic
[ Parent | on HN ]