All tags
Company: "zed"
not much happened today
claude-code gemini qwen3-coder gemini-2.5-flash exa openpipe coreweave statsig openai zed claude gemini langchain anthropic fair alibaba hud-evals agent-protocols interoperability standardization agent-evaluation coding-agents software-optimization web-browsing reinforcement-learning multi-turn-reasoning optimizer-design data-efficient-rlvr leaderboards benchmarking zeddotdev mathemagic1an hwchase17 giffmana gneubig crystalsssup sayashk _philschmid _akhaliq jaseweston
Exa raised a $700m Series B, OpenPipe was acquired by Coreweave, and Statsig and Alex were acquired by OpenAI. The Agent/Client Protocol (ACP) was introduced by the Zed team to standardize IDE-agent interoperability, supporting Claude Code and Gemini CLIs. LangChain 1.0 alpha unifies content blocks for reasoning and multimodal data. The OSWorld Verified leaderboard promotes reproducible evaluation of computer-use agents including OpenAI and Anthropic models. FAIR revealed coding agent cheating on SWE-Bench Verified. PR Arena hosts live coding agent competitions. Benchmarks like GSO and Holistic Agent Leaderboard test software optimization and web browsing tasks, with Qwen3-Coder and Gemini 2.5 Flash showing strong performance. Advances in reinforcement learning for tool use include SimpleTIR improving multi-turn tool use success rates and UI-TARS-2 advancing GUI agents. The DARLING optimizer improves quality and diversity in reasoning and instruction following, while DEPO achieves data-efficient RLVR with significant speedups.
Anthropic launches the Model Context Protocol
claude-3.5-sonnet claude-desktop anthropic amazon zed sourcegraph replit model-context-protocol integration json-rpc agentic-behaviors security tool-discovery open-protocol api-integration system-integration prompt-templates model-routing alex-albert matt-pocock hwchase17
Anthropic has launched the Model Context Protocol (MCP), an open protocol designed to enable seamless integration between large language model applications and external data sources and tools. MCP supports diverse resources such as file contents, database records, API responses, live system data, screenshots, and logs, identified by unique URIs. It also includes reusable prompt templates, system and API tools, and JSON-RPC 2.0 transports with streaming support. MCP allows servers to request LLM completions through clients with priorities on cost, speed, and intelligence, hinting at an upcoming model router by Anthropic. Launch partners like Zed, Sourcegraph, and Replit have reviewed MCP favorably, while some developers express skepticism about its provider exclusivity and adoption potential. The protocol emphasizes security, testing, and dynamic tool discovery, with guides and videos available from community members such as Alex Albert and Matt Pocock. This development follows Anthropic's recent $4 billion fundraise from Amazon and aims to advance terminal-level integration for Claude Desktop.