Waymo Launches Fully Autonomous Operations with 6th-Gen Driver
Waymo has initiated fully autonomous operations with its new 6th-generation Driver, aimed at expanding their service to more cities while reducing operational costs. This system is designed to handle diverse environments, including extreme winter weather, by utilizing a comprehensive set of sensors. The Waymo Driver has over 200 million autonomous miles of experience, underscoring its refined safety capabilities.
Central to the 6th-generation system is its multi-modal sensing suite comprising high-resolution cameras, advanced imaging radar, and lidar. These components work collectively to tackle the 'long tail' of rare driving scenarios. The vision system features a next-generation 17-megapixel imager, providing superior resolution, dynamic range, and low-light sensitivity. These capabilities allow the system to 'see' with fewer cameras, enhancing decision-making processes.
The lidar technology employed paints a detailed 3D point cloud of the surroundings, delivering precise distinction between small and large objects, irrespective of time or weather conditions. Additionally, cost reductions in the industry have allowed Waymo to construct these systems with reduced financial overhead while maintaining superior efficacy.
Waymo has also invested in custom silicon chips to handle increased processing requirements, reducing the need for additional hardware components. This configuration offers enhanced system performance and efficiency, even as camera numbers have been halved compared to the previous generation.
📖 Read the full source: HN LLM Tools
👀 See Also
Maryland Residents Hit with $2B Grid Upgrade for Out-of-State AI Data Centers — State Files FERC Complaint
Maryland's Office of People's Counsel filed a FERC complaint against PJM Interconnection, which allocated $2 billion of a $22 billion grid upgrade to Maryland customers — costing residential users ~$345 each, primarily to benefit out-of-state AI data centers.
Developer Seeks Architecture Advice for Serving Embed, Rerank, and Zero-Shot Models on 8GB VRAM
A developer building a unified Knowledge Graph/RAG service for a local coding agent is struggling with memory constraints on 8GB VRAM and 16GB system RAM, experiencing OOM errors, latency spikes, and Linux kernel kills when serving three transformer models concurrently.
Coasty AI Agent Solves CAPTCHA Challenges Up to Level 6 Without Training
Coasty's Computer Using Agent (CUA) achieved 82% on the OSWorld benchmark, solving CAPTCHAs up to Level 6, browser popups, and cookie banners without specific training for 'I'm not a robot' challenges.
Claude Code Opus Fails with Rate Limit Error Despite Available Weekly Capacity
A Claude Max subscriber reports that Claude Code Opus returns 'API Error: Rate limit reached' even though their usage dashboard shows 97% of their weekly 'All models' capacity remains unused. The issue occurs specifically in Claude Code while Opus works normally on claude.ai from the same account.