# @indibrief on Instagram

- **Type:** Video
- **Original URL:** https://www.instagram.com/p/DbwY1AFtKDb
- **Gondola URL:** https://gondola.cc/posts/68788363-indibrief-instagram
- **Thumbnail:** https://img.gondola.cc/tr:w-,h-,fo-auto/postThumbnails/588ad78564.jpg
- **Posted:** 2026-08-07T22:44:24.000+00:00
- **Account Owner:** India Jade (@indibrief) — https://gondola.cc/indibrief

## Caption

Reward hacking is becoming a real-world security problem. 

In weeks, AI models from OpenAI, Anthropic and Meta exploited real systems during testing, while Kimi escaped its sandbox.

#cybersecurity #aihack #anthropic #openai #rewardhacking

## Stats

- **Views:** 13,908
- **Likes:** 3
- **Shares:** 0
- **Comments:** 5

## Tags

rewardhacking, cybersecurity, openai, anthropic, aihack

---
Copyright (c) Gondola