No new models shipped this weekend, so the news came from the meter and the rulebook around agents, with OpenAI pooling ChatGPT and Codex usage, a user reporting Anthropic cut off a training workflow, and Claude Code adding budget and write limits.

No new models shipped this weekend, so the news came from the meter and the rulebook around agents, with OpenAI pooling ChatGPT and Codex usage, a user reporting Anthropic cut off a training workflow, and Claude Code adding budget and write limits.

With no major launches over the weekend, the signal came from builders publishing what agents cost and where they stall, while the vendor side moved through unannounced refusals and unshipped kernel fixes.

In three unrelated stories this week the outcome was set by code around the model rather than the model, a stealer that switches providers when one refuses, a ChatGPT takeover built from a bundled math library, and a new coding harness whose author says its permission prompts are not security.

The layer underneath the model is where this week's behavior and risk got decided, from a kernel bug an AI model weaponized through a Go default to a study showing the same tools behave differently as MCP or CLI.

The coding-agent failures disclosed on October 30 sat in the plumbing around agents, an editor's extension marketplace and a deployment platform's secret store, while a new benchmark shows the agents themselves are weakest at knowing when to stop and ask.

The most useful agent evidence this week came from people measuring agents at work, in game swarms, citation trails and red builds, and all three put the failure in coordination and checking rather than raw model skill.

GitHub's Universe releases turn coding agents into repository infrastructure, compiled into Actions, owned by the repo and billed to the org, and the same day it shipped the pinning and permission controls that make that safe to adopt.

Agent work is moving off the screen into schedules, background loops and managed harnesses, so the spend and behavior that matter now show up in telemetry instead of the chat window.

Unslop treats AI-looking UI as a predictable set of failures, so it audits first, stops for a one-screen direction, then fixes nine passes…

The numbat leak shows a frontier label can collect thousands of downloads with no provenance, and the real danger in trying such a model is…

Floorplan is worth installing because most of its map comes from parsed code while the AI names the parts and fills in the links code…

When an AI agent writes the code, framework choice becomes a cost line, because one 12-framework test found the same app cost almost twice…

The VOLTA infostealer treats a model's refusal as a retry condition by falling back across three providers, so defenders should put their…

Lexifina/global-law stores many countries' law as one git history ordered by in-force date and serves it through a read-only MCP server, so…

CVE-2026-98432 shows that an AI-built exploit reaches ordinary servers through defaults nobody chose, like Go turning on MPTCP listeners,…

Vercel-labs/agent-desktop makes desktop agents more reliable by reading the accessibility tree and tying every element reference to its…