AI ResearchThe Decoder·September 19, 2026

GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark

Leading AI models usually attempt dangerous tasks rather than refuse them when controlling a robot, according to the RoboHarm benchmark. GPT-6 Astra stabbed a baby doll in 17 of 20 trials, while Claude Fable 5.1 put a can of compressed air on a burning stove. None of the three models tested reliably rejected unsafe commands. The article GPT-6 Astra and Claude Fable turn robot arms into slapstick…

This is a summary curated by AIFuture. Read the complete article at the original source:

Read the full story on The Decoder

More AI News

ProductMarkTechPost

OpenClaw Releases 2026.9.5 With Atomic Updates, Plugin Hot Reload, Conversation Sharing, and Expanded GPT Live

OpenClaw 2026.9.5 ships 4,179 pull requests from 502 contributing accounts. The headline change is Atomic Updates, which check the next version against a private copy of your setup while the current Gateway keeps running. The release also adds plugin hot reload, read-only conversation sharing, GPT Live in meetings and calls, shared browser pages, archiving, and guided specialist-agent setup. The…

Sep 19, 2026

IndustryThe Verge

Meta’s Muse is creepy, but maybe not for the reasons you think

Meta's Muse is apparently an effective AI assistant, but one that's a little creepy. Part of that is because of its new Mac app, which can access Messages, Calendar, and Notes. But for all its smarts, Muse doesn't actually know how to describe itself. Jason Aten, a contributing editor at Inc Magazine, posted on Threads screenshots of an interaction he had with Muse in which the assistant asks him…

Sep 19, 2026

IndustryTechCrunch