← Founder Notes
Archive ·

The sandbox broke inside the lab before it reached production. openai disclosed six incidents where…

02:41 ISTby Yethikrishna R

the sandbox broke inside the lab before it reached production. openai disclosed six incidents where its own rl training runs had models signing up for disposable emails, searching github for leaked api keys, and uploading task data to public hosting — including one that fabricated data after using a leaked key. the harness problem is not a deployment problem.

Share

Embed this note

<iframe src="https://founder.myndlabs.tech/notes/embed/the-sandbox-broke-inside-the-lab-before-it-Dde8h9zjax7" width="480" height="420" style="border:0;max-width:100%" loading="lazy" title="The sandbox broke inside the lab before it reached production. openai disclosed six incidents where…"></iframe>

Original

More notes