Claude Code v2.1.217 caps concurrently running subagents at 20 by default, turns nesting off by default, and applies the cost ceiling to background subagents too. We read this update — where a tool that has steadily expanded autonomy pulls its parallelism defaults toward the safe side — through the
Bun was fully ported from Zig to Rust—530,000 lines in 11 days—by running multiple coding agents in parallel. We lay out the scale and motivation of the case, what it means for development teams, and the criticism that mass generation without review can't be trusted.
Claude Code v2.1.216 is an update with no eye-catching new features, but its changes share a consistent theme. It plugs the handoff leaks—where an agent reverts to defaults or reaches outside its isolation—around resuming, backgrounding, and worktree isolation, and it also eliminates the several-sec
On July 17, Cursor updated its Slack integration. It now returns a plan before starting a request, works across environments spanning multiple repositories, and can read and write across other channels and threads. Here we lay out these usability refinements for the chat-resident development agent,
On July 20, Anthropic makes its top-tier Fable 5 model a permanent fixture in Max and Team Premium — but limits it to 50% of the reduced usage cap, while Pro and Team Standard get a one-time $100 in credits before falling back to metered billing. Here's what it means for pricing and how you use it.
Claude Code v2.1.215 stops the agent from running /verify and /code-review on its own. It's a single-line change, but it's part of a three-release run — budget, permissions, now autonomy — that keeps narrowing what the agent does unprompted. When to invoke them is now your design decision.
Claude Code v2.1.214 is about fixes, not features. It closes five holes in permission checking, including a PowerShell 5.1 bypass, overly broad dir/** matching, and parsing failures on commands over 10,000 characters. Here's what to check today if you run the agent unattended.
OpenAI has released its first in-house hardware, the $230 Codex Micro. Six keys show the state of your Codex agents in color, and a dial turns reasoning depth up or down. A look at what it means that supervising agents in parallel has become enough of a job to justify dedicated hardware.
In Claude Code v2.1.212, the meaning of /fork changed. It's now the command that clones the conversation and launches a separate background session, while the old "child task, right here" behavior moved to /subtask. Here's a look at the update that lets you choose between running in parallel and del
Moonshot AI released Kimi K3 on July 16. With 2.8 trillion parameters and a 1M-token context, it lands near the top of coding leaderboards — but at $3/$15, its pricing now matches Sonnet 5. The weights are slated for July 27, and the "Chinese models are cheap" assumption has collapsed.
