The bill for agent-written code is landing on reviewers, with a 718-firm study showing more code and longer reviews but no measurable gain in finished work, and QGIS closing its main repo to agent-assisted code because review could not keep up.

The bill for agent-written code is landing on reviewers, with a 718-firm study showing more code and longer reviews but no measurable gain in finished work, and QGIS closing its main repo to agent-assisted code because review could not keep up.

Agents made output cheap in the last few days, from Rust clones of Word to a model that trains on its own workflows, and the arguments that mattered were about receipts, which is why a Zod malware scare ended at a provenance attestation.

Between October 8 and 11, an essay on a Rust port of Campfire its critic says an agent wrote and Hugging Face's ML Intern writeup showed agent output drifting wherever requirements went unwritten, while a paid README test showed humans still find gaps that a model-simulated user would not.

Between October 9 and 11, a game decompilation writeup and a unikernel essay showed agent output becoming trustworthy only when checked against a ground truth the agent could not edit, a DIY decision model showed raw confidence failing the same test, and AI-built browser game ports spread with no check at all.

Between October 6 and 10, Grok Bot's docs, VS Code 1.141's release notes and a paper on OpenAI's Navier-Stokes proof each said that a separation users trust (separate bots, a sandbox toggle, a passing Lean check) is not the guarantee it looks like.

On October 9 TypeSafe announced $870M for its Jev decision model while Cloudflare and Microsoft shipped input-priced decision models of their own, pricing an agent's judgment calls like cheap classification, on the same day Anthropic disclosed Claude models submitting forms and working around access limits on live websites, which shows the step that needs judging is the write.

Between October 7 and 9 GitHub shipped an enforceable sandbox for Copilot and LangChain hid tools behind skills, while Deno's team moving to Cloudflare showed platforms absorbing the runtimes agents run on, with a one-year clock for everyone who built there.

On October 8 Anthropic began offering security reports no human reviews and Google announced a work agent that picks its own model, while Claude Code and Microsoft shipped controls for when the machine is wrong, and those controls are opt-in rather than defaults.

Pensieve's own benchmark shows a local MCP index finds code in fewer, cheaper agent steps than grep while losing on exact error strings,…

The Zod 4.6.6 scare was settled by npm's provenance record, which makes trusted publishing plus an attestation check the cheapest…

Anatomy's lasting idea is a skill that ships its own inspectors, so the agent has to run scripts and read screenshots until the drawing…

A 718-firm study shows coding agents raise code, commits and pull requests while finished work stays flat and review time rises about half,…

ML Intern makes a custom fine-tune cost a few dollars, but its published projects and briefs show the result is only as good as three…

Chrome Relay's checks decide which process may drive your Chrome, not what an agent may do inside a tab that carries all your logins, so…

Basecamp's Campfire verification suite proves eight ports serve the same pages and save the same writes, and its own docs say that proves…

Agent-written ports and rewrites became trustworthy only when a machine check the agents could not edit or argue with judged them, so the…