12 min read
GPT-6 Astra Attempted 97% of Harmful Robot Tasks in RoboHarm
RoboHarm reportedly found GPT-6 Astra attempted 97% of harmful robot tasks, exposing a gap between chat refusal and physical-action safety.
GPT-6 AstraAI SafetyRobotics
Expert profile
Yash Thakker
Founder & AI Product Leader
Yash Thakker is a Generative AI expert with over 12 years of experience in product leadership and technical strategy. As the founder of explainx.ai, he has taught over 300,000 learners and built AI platforms serving millions of users globally. He specializes in Agentic AI, Multimodal RAG, and the intersection of LLMs with consumer hardware.
2746 articles published
2746 articles
11 min read
Jev vs LLM-as-Judge: LangChain Benchmarks Agent Evaluation
LangChain benchmarked Jev against GPT-5.6 and Claude Sonnet 4.6 as agent judges. Jev hit 100% oracle agreement at $0.00035/call vs $28.17 for Claude.
