Claude Opus

Anthropic's Applied AI team on the Evolution of Agentic Surfaces

Aug 11, 2026 · 31:24

Gagan Bhat and Isabella Kai He of Anthropic's Applied AI team explain how agentic surfaces evolved from the Messages API to the Claude Agent SDK and now Claude-managed agents, arguing that harnesses encode assumptions about model limits that go stale as models improve. They detail decoupling the brain (agent loop) from the hands (tool execution sandbox), which cut time to first token by 60% at P50 and over 90% at P95, and made failures recoverable via durable session logs. The session log also powers observability, context recovery, and 'dreaming,' a batch process that rewrites agent memory for self-improvement. They cover production lessons: keeping credentials in vaults, self-hosted sandboxes for VPC control, MCP tunnels for private servers, and the 'outcomes' feature that uses a grader agent to enforce success criteria.

Guide, Verify, Solve — Anirban Chatterjee, Sonar

Aug 9, 2026 · 22:31

Anirban Chatterjee of Sonar argues AI coding tools create verification debt: productivity spikes fade after three months while static analysis warnings and complexity persist, requiring zero-trust, multi-layered verification. A Carnegie Mellon study found the gain ran out at three months; a Wharton study showed humans followed AI advice 92.7% when correct but nearly 80% when it lied, while Sonar's leaderboard grades Claude Opus 4.6 and Sonnet 4.6 across correctness, reliability, maintainability, security, and complexity. He proposes the ACDC loop: guide agents with constraints, verify via SonarVortex, remediate automatically; SonarQube and Guitar verify in CI/CD, the latter with automated PR merging. Sonar says 7 million developers analyze 750 billion lines of code daily with it.

Ralph Loops: Build Dumb AI Loops That Ship — Chris Parsons, Cherrypick

May 4, 2026 · 1:48:26

Chris Parsons argues that dumb loops—simple while loops where an AI agent repeatedly executes the same task, evaluates its output, and iterates—outperform complex multi-agent orchestration and planning graphs. In this hands-on workshop, he builds a Pomodoro timer using Claude Code, implementing tickets one by one in a loop that self-corrects with each pass. He demonstrates the 'loop' command in Claude Code for scheduled, continuous execution and shows how to use sub-agents for adversarial validation to avoid self-confirmation bias. The talk covers real-world applications such as a worker loop that processes project steps overnight and a morning loop that generates daily briefings, all designed to offload routine work while keeping human oversight for irreversible decisions. Parsons emphasizes that the bottleneck in AI-augmented teams is often the review process, not coding speed, urging teams to identify and fix their biggest constraint first.

The State of MCP observability: Observable.tools — Alex Volkov and Benjamin Eckel, W&B and Dylibso

Jun 20, 2025 · 16:56

Alex Volkov (Weights & Biases) and Benjamin Eckel (Dylibso) argue that MCP-based AI agents create observability blind spots, and that OpenTelemetry-based distributed tracing, combined with community initiatives like observable.tools, can provide end-to-end visibility. They show how Weave's MCP support and mcp.run's upcoming OTel export enable tracing across client and server, using context propagation via MCP's metadata to stitch traces together. Volkov shares a meta story where Claude Opus 4 used MCP to automatically fix its own observability code, discovering and querying a support bot without human intervention. The episode calls for tool builders to adopt OTel and join semantic conventions efforts for agent observability.

AI Frontiers in Trust and Safety Combatting Multifaceted Harm on Tinder at Scale: Vibhor Kumar

Dec 2, 2024 · 14:36

Vibhor Kumar, senior AI engineer at Tinder, explains how the company uses open-source LLMs and LoRAX to detect a long tail of trust and safety violations at global scale. Facing challenges like content pollution and automated fraud from generative AI, Tinder leverages pre-trained models such as LLaMA and Mistral, fine-tuning them with LoRA and QLoRA on hybrid datasets generated by GPT-4 and manually verified. They serve dozens of fine-tuned adapters on a single GPU using LoRAX, achieving real-time inference (tens of QPS, ~100ms latency) for categories including hate speech, pig butchering scams, and underage users. The approach yields near 100% recall on simpler tasks and significant improvements over baselines, with better generalization that resists adversarial evasion. Future directions include visual language models for explicit image detection and automating retraining pipelines.

Building State of the Art Open Weights Tool Use: The Command R Family: Sandra Kublik

Aug 26, 2024 · 15:03

Sandra Kublik of Cohere presents the Command R family of open-weight models optimized for retrieval-augmented generation and tool use. Released in March 2024, Command R and Command R+ achieved 150,000 Hugging Face downloads within two weeks and now serve nearly 500,000 developers. The models overcome RAG challenges such as prompt sensitivity and citation accuracy through post-training, delivering fine-grained citations and low hallucination. Cohere open-sourced a toolkit UI with plug-and-play components for RAG and tool use, supporting cloud, local, and Hugging Face access. The new Multi-Step API enables sequential reasoning with automatic retry and reflection. Command R+ matches GPT-4 Turbo and Claude Opus on complex reasoning while being three to five times cheaper, positioning it as a scalable enterprise solution.