Results for “autonomous-driving”

Dolphins: Multimodal Language Model for Driving

Give your agent a budget, a target, and a deadline — it does the rest. Orchestrates DSL + Opportunity Scanner + Emerging Movers into a full autonomous trading loop on Hyperliquid. Race condition prevention, conviction collapse cuts, cross-margin buffer math, speed filter. 3 risk profiles: conservative, moderate, aggressive. Use when setting up autonomous trading, creating a trading strategy, or running a scan-evaluate-trade-protect loop.

Run automated hyperparameter optimization for NVIDIA TAO models using AutoMLRunner, supporting multiple search algorithms and experiment tracking.

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Full autonomous execution from idea to working code

Expert en robotique avancée (ROS, SLAM, manipulation, autonomous navigation, DZ context)

Use when a carrier asks about autonomous trucks — current state of Level 4 development, major programs (Aurora, Kodiak, Plus, Waymo Via, Embark history), regulatory status, operational implications, hub-to-hub model, driver impact, insurance, and what carriers should be doing now (or not doing) to prepare.

Run Claude Code autonomously in loops, from simple sequential pipelines to multi-agent DAG orchestration.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Clade goal-driven autonomous improvement loop (Blueprint architecture — deterministic pre/post phases + LLM supervisor/worker nodes, converges when goal met or max-iter hit). NOT the Claude Code built-in /loop (which polls a prompt on an interval like `/loop 5m /foo`) — if the user wants interval polling, route to the built-in.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture for rapid experimentation and synthesis, producing papers and presentations.

Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.

Analyzes game AI systems in a codebase, covering behavior trees, finite state machines, GOAP, utility AI, pathfinding, steering, perception, difficulty adaptation, NPC dialogue, and AI debugging tools for Unity, Unreal, and Godot projects.

Builds reliable browser automation skills by iteratively running a browsing task, reading the trace, and improving the navigation strategy until it passes consistently.

Continuously monitors system performance, identifies improvement opportunities, and orchestrates skill discovery and creation to autonomously evolve capabilities.

Train, evaluate, export, prune, and run inference for PointPillars 3D object detection models from LiDAR point clouds using NVIDIA TAO.

Walk through the manual-capture.md checklist for a slug, driving Chrome via the Claude in Chrome MCP to capture each visual that needs more than a static URL — multi-step flows, conversation states, settings panels, age gates on third-party sites. Runs equally well locally (your desktop Chrome) or on a VPS with always-on Chrome + the extension installed. Defaults to unattended mode when `BLOG_AGENT_AUTONOMOUS=1` (which forces `UNATTENDED=1`). Use after /generate-visuals has flagged action-shot or failed-screenshot entries.