Request an AI-driven robot arm to put a screwdriver in a toaster, and it might just try.
When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works .
GPT-6 Astra attempted harmful actions 97% of the time when it was asked to stab a human-like figure, heat compressed gas, or produce toxic fumes, succeeding in 62% of its attempts. Fable 5.1 refused more often, attempting 80% of trials and completing 34%. September 18, 2026
Robocurve is a “Public Benefit Corporation helping society understand the state of robot intelligence,” according to the company. Its Y Combinator page highlights this as building “open-source tools and independent benchmarks to measure how well robots can do real-world jobs.” The I2RT arms used in the test list at $2,999 each, and the company’s test relies on giving the two frontier LLMs camera images with arm positions issued through tool calls.
The Fable model had 20 refusals out of 100, but all of these were on the doll task. It was 0 out of 80 on the rest. Meanwhile, Astra had 0 out of 20 safety refusals on the same doll task, and its two came on the burner and power bank tasks. The doll instruction is the only one that names a violent act, but it is also the only scene with a human-like target, so the test cannot separate the wording from the target.
Outside of this, all three models together only produced two safety refusals for the doll task. The willingness to do the task is different from being successful in carrying it out. Where the models did attempt a task, MolmoAct2 completed 6 of 71, Fable 34 of 80, and Astra 60 of 97.
Fable’s refusals each took a single model call and one step with a median of 23 seconds, against Astra’s 15 calls, 154 steps, and 107 seconds median over its 19 non-refused doll trials. The published transcript reads, “I’m not willing to have a real robot perform a stabbing motion.” MolmoAct2’s lack of refusals is another matter, as it is a different kind of model. Eight days before RoboHarm, the model completed 0 out of 100 on Robocurve’s StationeryBench; “its low completion rate reflects capability, not safety,” the RoboHarm report says.
Anthropic CEO warns of AI-driven botnet 'swarm' taking over the entire internet
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/artificial-intelligence/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/artificial-intelligence/ai-controlled-robot-arms-attempted-harmful-tasks-97-percent-of-the-time-experiments-included-stabbing-a-baby-doll-mixing-chemicals-openai-and-anthropic-models-try-mixing-bleach-and-stabbing-dolls-without-jailbreaks#main
- https://www.tomshardware.com/membership
- AI-controlled robot arms attempted harmful tasks 97% of the time; experiments included stabbing a baby doll, mixing chemicals — OpenAI and Anthropic models try
- TypeSafe AI's Jev offers an alternative to LLMs that claims to be 193x faster and 445x cheaper — System One type model is bespoke for probabilistic decision-mak
- ‘Now We Can Know Everything and Do Anything,’ Jensen Huang Says at Dreamforce
- University of Manchester Uses NVIDIA Earth-2 to Forecast Air Pollution Across the UK
- Kash Patel says that AI use at the FBI has 'increased by 605%' since he became director — claims that every major tech player is 'embedded' in the agency
Informational only. No financial advice. Do your own research.