Breaking · This week
This week in AI, for builders
Short notes on what actually changed: each with the primary source and one line on why it matters if you build things. The last 14 days are at the top; older notes are archived below.
Last 14 days
Why it matters: If your agents run code or browse, the fix is classic security: sandbox them, restrict network egress and watch what they do, rather than trusting model guardrails.
Source: CSO Online ↗Our pick: E2B sandboxes for agent code execution
Google releases Gemini 4 Argon (opens in new tab)
Why it matters: A new frontier model aimed at long-horizon coding and agent work, with up to 1M output tokens; worth re-running your own evals before switching defaults, since vendor benchmarks mix wins and losses across tasks.
Codex CLI auto-starts a persistent, self-updating background daemon (opens in new tab)
Why it matters: Since 0.157.0 an interactive session leaves a daemon running that updates itself hourly and keeps the first session's env vars (e.g. proxies); if you need predictable installs, run codex features disable daemon_auto_start and stop the daemon.
Source: GitHub (openai/codex issue #48195) ↗Our pick: OpenAI Codex CLI
OpenCode 2.0: background service, new API and SDK, MCP code mode (opens in new tab)
Why it matters: Breaking upgrade (opencode upgrade --major): 1.x plugins and the old server API stop working, but you get background subagents, scriptable sessions via @opencode/client, and MCP servers exposed as callable code by default.
Newsletter
Practical discoveries, without the noise.
The best new agent workflows and tools we've vetted, with a clear verdict on each. Short, occasional, useful.