Context-Window

The Model Context Protocol (MCP) was supposed to be the universal connector for agentic AI — a standard way for agents to call tools without custom glue code. But at Ask 2026, Perplexity CTO Denis Yarats dropped a significant signal: Perplexity is moving away from MCP internally, and the reason has major implications for anyone building production agentic systems. The Problem: 55,000 Tokens Before Your Agent Does Anything Yarats was direct about the technical issue. MCP tool definitions — the schema declarations that tell an agent what tools are available and how to call them — were consuming 55,000+ tokens before a single user message was processed. ...

If you’ve been hesitating to build long-context workflows because of the cost, Anthropic just removed the last excuse. As of March 13, 2026, the full 1 million token context window is generally available for both Claude Opus 4.6 and Claude Sonnet 4.6 — at standard API pricing, with no premium multiplier attached. That’s a significant shift. Until now, heavy long-context usage carried an implicit tax: either you paid a premium rate for requests over certain thresholds, or you engineered around the limitation with chunking, compaction, and lossy summarization. Those workarounds aren’t free — they cost engineering time, introduce accuracy loss, and add system complexity. Anthropic is now saying: stop doing that. ...

The agentic AI landscape just shifted. OpenAI’s GPT-5.4 — launched March 5, 2026 — isn’t just a model update. It’s a direct bid to own the autonomous agent stack, arriving with native computer-use, a one-million-token context window, and a reworked tool-calling system that slashes token consumption by 47% on MCP benchmark tasks. If you’re building with agent pipelines, this is the model release worth paying attention to. What’s Actually New in GPT-5.4 Native Computer-Use This is the headline feature, and it’s genuinely significant. Rather than bolting computer-use on as a post-hoc capability, OpenAI has built it into GPT-5.4 at the architecture level. The model can observe screen states, click UI elements, type into fields, scroll, and navigate applications — autonomously, without requiring a separate vision model or operator middleware. ...

Anthropic Releases Claude Sonnet 4.6 — 1M Token Context, Flagship Agentic Performance On February 17, 2026, Anthropic released Claude Sonnet 4.6, and the agentic AI community immediately took notice. This is the model that now powers OpenClaw by default — and for good reason. Sonnet 4.6 brings a 1 million token context window in beta, dramatically improved agentic task performance, and holds its price point at the same level as Sonnet 4.5. Flagship performance at mid-tier cost. ...