Writing

From the field.

What Jigar learns building and training, shared as posts. Specifics over slogans.

Showing 19–27 of 123

November 2, 2026 cover for Claude message threads and GLM-Legal
Architecture12 min

November 2 agent guide: Claude message threads and GLM-Legal

November 2, 2026 cut upload cost for long agent loops. Anthropic put message threads into public beta on the Messages API, reporting about 35% lower median time to first token on 500K to 1M token Claude Code requests. Z.ai also opened GLM-5.3-FlashX-Legal for MCP-connected legal workflows, and xAI retired grok-imagine-image-quality.

Nov 2, 2026Read
November 1, 2026 cover for Mage-VL-Cowork hybrid computer use
Architecture10 min

November 1 agent guide: Mage-VL-Cowork hybrid computer use

November 1, 2026 put Microsoft Mage-VL-Cowork in front of builders: a 4B hybrid computer-use agent that combines GUI actions with persistent bash and Python, reporting 66.0% on OSWorld-Verified under a 50-step budget. Weights ship under Apache 2.0.

Nov 1, 2026Read
October 31, 2026 cover for DeepSeek Super-agent and Claude Code policy
Architecture10 min

October 31 agent guide: DeepSeek Super-agent and Claude Code policy

October 31, 2026 added a DeepSeek Super-agent research prototype that is not a product, and Claude Code controls for layered policy, pooled budgets, and Bedrock guardrail input tagging. A later design essay on November 1 points at the same prototype.

Oct 31, 2026Read
October 30, 2026 cover for Claude Code write blocks and gateway groups
Claude9 min

October 30 agent guide: Claude Code write blocks and gateway groups

October 30, 2026 is a Claude Code control release, not a new model. The changelog adds a write block outside working directories, gateway groups on upstreams, and idle compaction. Opus 4.8 fast mode is deprecated the same day and is removed November 30.

Oct 30, 2026Read
October 29, 2026 cover for the Cursor marketplace incident and Mistral Large 4 weights
Architecture12 min

October 29 agent guide: Cursor marketplace incident and Mistral Large 4

October 29, 2026 was a supply-chain day and a weights day. Cursor reported tampered Claude Code extension packages in its marketplace. Mistral published open weights for Large 4 under the Ecosystem Open-Weight License. Official Anthropic Claude Code was not the compromised artifact.

Oct 29, 2026Read
October 28, 2026 cover for Copilot MCP connectors and Gemini 4 Carbon
Architecture11 min

October 28 agent guide: Copilot MCP connectors and Gemini 4 Carbon

October 28, 2026 added verified MCP connectors for GitHub Copilot and opened Gemini 4 Carbon as a Fairwind cyber-defender model. Carbon is not a general coding default. Gemini Robotics-ER 2 is a parked robotics preview from the October 27 post.

Oct 28, 2026Read
October 27 agent guide cover listing Copilot SDK identity, Claude Code 2.1.311, Liquid LFM3, and Genie 4
Architecture16 min

October 27 agent guide: Copilot SDK identity, LFM3, and Genie 4

October 27, 2026 gave organization-owned Copilot SDK apps their own identity, a Claude Code release that keeps long sessions moving, and an open-weight 2B family built for on-device agents. Genie 4 arrived the same day as a research preview, not as a production runtime.

Oct 28, 2026Read
Cover diagram for OpenAI agent automations, Claude Code 2.1.310, Copilot CLI Autopilot, and Nanbeige4.3-33B on October 24-25 2026
Architecture15 min

Scheduled agent runs: OpenAI automations, Claude Code 2.1.310, and Nanbeige4.3-33B

October 24, 2026 added a cron for OpenAI agent sessions, a Claude Code control release, a Copilot CLI Autopilot wait fix, and an Apache 2.0 33B agent model. October 25 did not add a second primary model launch.

Oct 26, 2026Read
Cover diagram for the October 22-23 2026 agent routing board: Kimi K3.1 Pro, OpenAI Decisions API, MiniMax M3.1 Flash weights, and NVIDIA Nemotron Bolt
Architecture16 min

Kimi K3.1 Pro and the October 22-23 agent routing board

On October 22 and 23, 2026 Moonshot opened Kimi K3.1 Pro, OpenAI made the Decisions API generally available, MiniMax published M3.1 Flash weights, and NVIDIA shipped an on-device conversational agent model. This guide covers what actually shipped, what is still vendor-reported, and how to place each lane.

Oct 24, 2026Read