What each daily research pass changed, newest first. Every change is checked against a primary source. The lab landing page shows the latest three.
Agentic Engineering: the Vercel microVM escape now has a CVE and fixed kernels, and a new item on an Agent SDK flaw where a session ID became a command-line flag.
One Agent to Hundreds: checks you have seen fail (pstack's new formal verification skill), Addy Osmani on layered verification instead of line-by-line review, and pstack's updated catch-up rules.
Did the Agent Do It Right?: graders can be reward-hacked too, and why each eval task gets its own microVM.
Smaller: DeepSeek's search and fetch billing for failover (Plan B), a Docker Hub token gotcha (Security), Microsoft on prompts as no enforcement boundary (Agentic), Boris Cherny on Claude Code Review (fleet).
New: Graphs and Loops, Drawn. What it means to stop prompting and build the loops and graphs that prompt your agents, who really said it, whether to draw or describe them, and how to get your agent to build them.
One Agent to Hundreds: Lauren Tan's “inverse pyramid” for trusting agent work, Birgitta Böckeler on dropping test-first prompts, Dex Horthy's SlopCodeBench results, the Claude Code team's risk-tiered review, and how Amp gates deploys without pull requests.
Plan B: DeepSeek-V4.1-Flash-1017 adds MIT-licensed open weights, and a new note on why failing over costs you the prompt cache.
Plan B: OpenCode's breach, tied to a distillation attack on users with linked provider keys, and what it means for keys you hand to a harness.
Engineering on an Exponential and Engineering for the Next Agent: Epoch's new price trend (about 13x cheaper a year for the same performance) replaces its March 2025 range.
Verification research on One Agent to Hundreds and Did the Agent Do It Right?: what agents' reports leave out, where judges place the first mistake, monitors fooled by edited transcripts, and self-grading loops.
Smaller: Claude Code 2.1.302 fork-subagent default (fleet), Copilot approvals preview (Ownership), an OpenTelemetry versioned-metrics gotcha (Observability), Anthropic's agent-hours data (Exponential), pstack wording (Agentic), a harness-dependence example and METR's cheating caveat, and this changelog.
Engineering on an Exponential: frontier models now leapfrog each other every few weeks, not every few months; a full source check of it and of Engineering for the Next Agent.
Fleet and agentic pages: Opus 5.5 fast mode out of research preview, Claude Code Review GA, context resets, review backpressure, XBOW's parallel campaigns, Amp's SOC 2 without pull requests.
Smaller: about 60 edits across agent evals, Linux, Kubernetes, Terraform and patterns; moved GitHub links on four pages; a site icon.
Plan B: Meta's Muse Spark Open weights make open models a failover tier again.
Agent security: the SneakPeek preview-pane flaw, a Vercel microVM escape, Letta subagent permissions, a Deep Agents symlink fix.
Smaller: 27 edits across nine pages, including Kubernetes readiness, reviewer simulations, Claude's OpenTelemetry GenAI traces, Prometheus MCP and GitHub autofix.
Gemini 4 Argon GA, added as a dated example of an API change; pstack 0.15.24 updates on Agentic Engineering.
Smaller: 21 edits across agentic, fleet, Terraform, IaC, Kubernetes, security and delivery (Kiro sandbox GA, a Copilot for Visual Studio CVE, Terraform MCP, kubectl-ai, GitHub Actions workload identity).
15 fixes on seven pages: IaC drift and lock timeouts, AWS SourceIdentity provenance, Linux effective memory.min, Transparent Huge Pages stalls, Prometheus 3.15 native histograms.
Smaller: a dead link replaced and per-version Terraform changelog links.
The Incident Files: two new records, Docker Hub PAT transfer and Fly.io readiness checks (318 in all).
Smaller: TLS 1.3 now cites RFC 9846, an agent-team permissions note, a restored Cloudflare incident link and Kubernetes doc links.
39 verified fixes in 18 files: stale versions, Datadog renames, the MCP 2026-07-28 spec, SLSA v1.2, OpenTelemetry Profiles alpha, and three Incident Files records.
Smaller: moved links and accuracy fixes in the ownership essay.