# @futurewalt.ai on Instagram

- **Type:** Image
- **Original URL:** https://www.instagram.com/p/Ddw71G3kwez
- **Gondola URL:** https://gondola.cc/posts/71025196-futurewaltai-instagram
- **Thumbnail:** https://img.gondola.cc/tr:w-,h-,fo-auto/postThumbnails/2032912f84.jpg
- **Posted:** 2026-09-26T20:51:28.000+00:00
- **Account Owner:** Ai | ainews | aitools | futurewalt.ai (@futurewalt.ai) — https://gondola.cc/futurewalt.ai

## Caption

AI ROBOTS JUST FAILED A SERIOUS SAFETY TEST. 🤖⚠️

RoboHarm tested three AI robot systems on physical safety tasks.

The reported results:

• GPT-6 Astra — 60% of harmful actions completed
• Claude Fable 5.1 — 34%
• MolmoAct2 — 6%, but refused none

The interesting part is that lower completion of harmful actions doesn’t necessarily mean better refusal behavior — MolmoAct2 reportedly completed fewer harmful actions while also refusing none.

These tests highlight a major challenge for AI robotics: making systems capable enough to act in the real world while ensuring they know when not to act.

AI safety gets a lot more serious when the model has a body. 🤖

#ai #robotics #aisafety #humanoidrobot #technology

## Stats

- **Views:** 0
- **Likes:** 0
- **Shares:** 0
- **Comments:** 14

## Tags

aisafety, robotics, technology, ai, humanoidrobot

---
Copyright (c) Gondola