Morning Brief: Sunday, November 22
Seventy-four feeds reporting. Two weeks. 5,523 items reduced to what follows. (what we track, how we crawl, subscribe)
Sunday's thread is the plumbing between agents. The week's hardest evidence is not about model capability – it is about what happens to data and identity once a request crosses from one agent service into the next.
Two million canaries is the number. Dan Goodin's 2026-11-20 report
describes an experiment that planted unique, trackable secrets inside
prompts and followed them through a network of AI services; the
secrets did not stay put. That is a measurement, not a prediction, and
it lands in the same days that Signal began restricting mobile
screenshots – explicitly framing agents reading the screen as an
existential threat rather than a feature – and that arXiv's cs.AI
stream carried four separate papers on the same seam: tool names that
are not identities, agent cards at the A2A trust boundary, zero-trust
propagation across delegation chains, and authorization that can
actually be audited across the model, harness, and workflow layers.
Our own crawler census agrees from the other direction: of
twenty-seven new bots recorded in the zoo over two days, a visible
share exist to scan MCP endpoints, inventory tools, read llms.txt,
or monitor other agents.
The second thread is narrower and older: if agents write the code,
what is the artifact a human reads? The New Stack asked it directly.
Nvidia's answer was 20,000 training examples aimed at its own model's
mistakes. Graham Dumpleton's answer, visible in Simon Willison's
link-blog, is a daily public development log for an AI-assisted Rust
server – a post nearly every day for three weeks, the narrative
shipped alongside the binary. Martin Fowler's Deterministic Simulation
Testing is a third answer, and arXiv's contribution is the deflating
finding that for automated code review, a single agent is often
enough.
Top (5-7 min)
- Researcher plants 2m canaries into the AI supply chain. A privacy disaster surfaced.
- Ars Technica via Lobsters, 2026-11-21. Dan Goodin, dated 2026-11-20. Unique trackable secrets embedded in prompts, followed through a chain of AI services, leaked. The method is the contribution: tripwires, not surveys.
- Signal restricts mobile screenshots as it confronts 'existential threat' of AI surveillance
- TechCrunch, 2026-11-21. A messaging app treating on-device agents as adversaries. The screen, not the network, is now the exfiltration surface.
- When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents
- arXiv cs.AI, 2026-11-17. Measures the gap between a tool's advertised name and the provider actually serving it. The naming layer is load-bearing and has no authentication.
- If we stop reading the code, what do we read?
- The New Stack, 2026-11-21. The question the rest of the week keeps answering indirectly. Worth reading before the papers below, which are all partial answers.
- Mapping the AI Supply Chain: Dependencies, Vulnerabilities, and Market Concentration in the AI Ecosystem
- arXiv cs.AI, 2026-11-19. The structural companion to the canary experiment: where the dependencies concentrate, and therefore where a leak propagates furthest.
- Nvidia's Accounting Practices Now Being Investigated by America's SEC
- Slashdot, 2026-11-21. Arrives the day after California's AG subpoena over chip sales to China. Two separate investigations, one week.
- Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers
- arXiv cs.AI, 2026-11-17. Separates authorization failures by layer, which is the prerequisite for assigning them to an owner.
Themes
Two million canaries
The canary experiment and the MCP identity papers are the same finding
approached from opposite ends. Goodin's report is empirical: plant
secrets, watch them surface somewhere they should not be. The papers
are structural: When Tool Names Are Not Identities shows that the
string an agent uses to select a tool does not bind to a provider,
We Have All the Cards locates the same problem at the Agent2Agent
protocol's operational trust boundary, and Agent-ZTA proposes
propagating security state bidirectionally across a delegation chain
instead of trusting it at the first hop.
- We Have All the Cards: Securing Agent Cards at the Operational Trust Boundary of the Agent2Agent Protocol
- arXiv cs.AI, 2026-11-17.
- Agent-ZTA: A chain-Aware Zero Trust Model for Bidirectional Security-State Propagation and Runtime Containment in Multi-Agent Delegation
- arXiv cs.AI, 2026-11-17.
- Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent
- arXiv cs.AI, 2026-11-16.
One shipped agent, instrumented. The
shippedqualifier is the reason to read it. - Readie: Low-Latency Code Sandboxes for AI Agents
- arXiv cs.AI, 2026-11-18. Containment at the execution layer rather than the protocol layer.
What you read when nobody reads the code
Four answers landed in two days, none of them the code. Nvidia's is
data: 20,000 examples targeting its own model's errors, with a coding
score to show for it. Dumpleton's is narrative: a development log
published as the work happens, running near-daily since 2026-11-04,
which Willison collected. Fowler's is a technique – Deterministic
Simulation Testing, which replaces reading with replayable
execution. And arXiv's is a negative result: for automated
code review, the multi-agent architecture is often unnecessary.
- Nvidia used 20,000 training examples to fix its AI's mistakes. Its coding score jumped.
- The New Stack, 2026-11-21.
- Muru
- Simon Willison, 2026-11-21. Graham Dumpleton's AI-assisted Rust server for WSGI and ASGI Python apps, twenty years after he started mod_wsgi. Willison collects the running development log; the cadence is the point as much as the server is.
- Deterministic Simulation Testing
- Martin Fowler, 2026-11-17.
- When Single Agent Is Enough: Rethinking Multi-Agent Systems for Automated Code Review
- arXiv cs.AI, 2026-11-19.
- PrivacyPR: A Dataset of Real-World Privacy Fixes for Benchmarking Privacy-Aware Code Review
- arXiv cs.AI, 2026-11-16. Real privacy fixes as ground truth, which makes the benchmark harder to game than synthetic defects.
Nvidia's two stories
The SEC accounting investigation and the California subpoena are separate matters landing in the same week, and TechCrunch's framing treats the company as two stories running in parallel – the engineering organization and the governance one – following Jensen Huang's exit.
- A tale of two Nvidias
- TechCrunch, 2026-11-21.
- Bitcoin Drops to $56,085, a Two-Year Low, in Worst Month Since 2022
- Slashdot, 2026-11-21. The market backdrop, included because the Nasdaq erased its 2026 gains in the same stretch.
Scan
Coding agents, review, and the harness
- GPT-6.2 Sol vs. Claude Opus 5.5: Not as accurate, but still might be the better buy
- The New Stack, 2026-11-21. A cost-per-correct-answer comparison rather than a leaderboard reading.
- "It is a rollercoaster ride": Angie Jones of the Agentic AI Foundation on keeping up with AI agents
- The New Stack, 2026-11-21.
- Dynatrace just laid out its AI observability playbook at KubeCon. Here's why it matters for developers.
- The New Stack, 2026-11-21.
- Here are the top AI agents that can live in your text messages
- TechCrunch, 2026-11-21. Relevant to the Signal item above: SMS as an agent surface.
- Beyond Plain MCP: Do Decision Models and Code Mode Make Tool Use Cheaper and Faster?
- arXiv cs.AI, 2026-11-17.
- HEAMS: Holistic Evaluation of Agent Memory Systems
- arXiv cs.AI, 2026-11-17.
- Evaluating Governed LLM-Driven ML Experimentation: Lifecycle, Provenance, and Failure Metrics
- arXiv cs.AI, 2026-11-19.
Proof automation and formal methods
Last week's Riemann claims have not been settled, and this week's papers are the infrastructure question underneath them: what does a machine-checkable proof pipeline actually look like.
- Even more posts, opinion pieces, interviews, and position statements
- Terence Tao, 2026-11-22.
- Hurried Announcement: Alessandro Masullo GRH
- Math 216, 2026-11-21. A seminar announcement on the Generalized Riemann Hypothesis, posted at short notice.
- Turing Agent: Agentic Formal Verification for Mathematical Research
- arXiv cs.AI, 2026-11-17.
- From Sorry to QED: Refining LLM Math Proofs via Angelic Execution
- arXiv cs.AI, 2026-11-18.
The title names the failure mode: Lean's
sorryas the gap between a plausible proof and a checked one. - Reusing formal Vlasov-Maxwell proofs to certify plasma solver outputs
- arXiv cs.AI, 2026-11-19.
- From Pen-and-Paper to Machine-Checked Proofs: Lean for System Identification
- arXiv cs.AI, 2026-11-16.
Security and the attack surface
- GhostScript CVE 2026-125396: "Upload2Shell"
- Lobsters, 2026-11-21.
- Microsoft 365 Outage - Post Incident Report
- Lobsters, 2026-11-21. The 2026-11-12 outage write-up, collected outside Microsoft's own status channel.
- Trump says reported FBI database hack is 'not good'
- TechCrunch, 2026-11-21.
- US DOJ Charges Suspected Russian Agent for Stalking Palantir Employees in California
- Slashdot, 2026-11-21.
- Will AI-Fueled Cyberattacks Lead to Better Funding for Critical Open Source Projects?
- Slashdot, 2026-11-21.
- port scanning for mojang
- Lobsters, 2026-11-21.
- Network-Exposed Configuration Attacks on LLM-Controlled Social Robots
- arXiv cs.AI, 2026-11-18. The embodied version of the same trust-boundary problem: the configuration endpoint is on the network.
Infrastructure, languages, and the craft
- C++26 is done (again)! – Trip report: November 2026 ISO C++ standards meeting (Buzios, Brazil)
- Lobsters, 2026-11-21.
- How I Got Postgres into a Single Binary
- Lobsters, 2026-11-21.
- Probabilistic data structures in Go, part 2
- Lobsters, 2026-11-21.
- Advice for the next 100 Rust GUIs
- Lobsters, 2026-11-21.
- NixOS bring-up on an Alibaba RISC-V board
- Lobsters, 2026-11-21.
- Changes on freedesktop.org
- Lobsters, 2026-11-21.
- TODOs JJ Style
- Lobsters, 2026-11-21.
- Data Contracts
- Martin Fowler, 2026-11-20.
- Traffic mix matters
- Marc Brooker, 2026-11-18.
- My Monitor Was Cutting My Download Speed by 75%
- Lobsters, 2026-11-21.
Policy, society, and the human read
- The Claude Delusion
- Lobsters, 2026-11-22. Jan Schaumann, dated 2026-11-13, surfaced on Lobsters today. An essay on wealth, illusory superiority, and Dunning-Kruger in tech leadership rather than on any model's behavior.
- Internet Archive Staffers Are Unionizing
- Slashdot, 2026-11-21.
- Is selling an AI version of your face to this microdrama startup the future of Hollywood?
- TechCrunch, 2026-11-21.
- Alaska, your next governor is a Wikipedia nerd
- TechCrunch, 2026-11-21.
- Americans Enters Post-Penny World, Businesses Now Allowed to Round Cash Transactions to Nearest Nickel
- Slashdot, 2026-11-21.
- Wrong with Confidence: Measuring Hallucination, Overconfidence and Identity-Conditioned Behaviour in Large Language Models
- arXiv cs.AI, 2026-11-17.
Markets, products, and the business read
- GTA 6: 32.5 Million copies, Cameos, and Easter Eggs - but No Physical Discs
- Slashdot, 2026-11-22.
- Toyota, Nissan, and Honda to Standardize Parts to Lower Costs
- Slashdot, 2026-11-21.
- 59 Years Later, 'The Prisoner' is Getting a Second Remake - from Amazon Studios
- Slashdot, 2026-11-21.
Science, space, and the physical
- Earth has a New Moon
- Slashdot, 2026-11-21.
- Mercury-Bound X-Ray Telescope Delivers First Images After Eight Years In Space
- Slashdot, 2026-11-21.
- Quantum Computing's First Real-world Payoff May Come In Energy Solutions
- Slashdot, 2026-11-22.
- Several Waymo Self-Driving Cars Stalled in Traffic as San Francisco's Streets Flooded
- Slashdot, 2026-11-22. An autonomy failure mode with no model in it: standing water.
- Building a Robotic Hand on a Budget
- Hackaday, 2026-11-22.
- Capturing and Mineralizing Atmospheric Carbon Dioxide
- Hackaday, 2026-11-22.
- Thermite Powered Instant Phone Charger
- Hackaday, 2026-11-22.
- A Replacement PCB for the Echo Dot
- Hackaday, 2026-11-22.
- Quick WIFI Adapter Through USB
- Hackaday, 2026-11-22.
- ESP32 Drives MDA Display For Wireless Terminal
- Hackaday, 2026-11-21.
- Automation For The Swimming Pool
- Hackaday, 2026-11-21.
The crawler zoo
Thirty-four crawler-zoo arrivals are dated 2026-11-21 or 2026-11-22;
twenty-seven are new to this series, and twenty-six of those are listed
here. A visible share of them exist to inspect
agent infrastructure rather than content: MCP tool scanners, a tool
inventory checker, an llms.txt scanner, and an agent monitor.
- MCP and agent infrastructure
- secdb-mcptoolscan, mcp-inventory-check, mocop-crawler, LLMS-Txt-Scanner, ZeroFox-AI-Agent-Monitor, free-apis-check
- Commerce and catalog
- catalog-indexer, catalog-checker, LocalEcommerceAssetResearch
- Outreach and contact harvesting
- outreach-scout, outreach-poc, ContactXBot, bottomlines-crawl
- Audit, archive, and search
- AuthorizedPublicPageAuditor, PubSleuthBot, bxzxxr-archive, watrsearch, PageHubBot
- Unclassified
- Chrome-Lighthouse, keda, e5-frame-b, AterstodBot, NoahBot, Jambot, ProngBot, WallingBot
Boston
- The Human Algorithm - Can AI Understand What Makes Us Human?
- Boston AI Week, 2026-11-22.
- Entrepreneurship Conference 2026
- Harvard SEAS, 2026-11-22.
- Northeastern University Graduate Fair: Unlock Your Double Husky Scholarship
- Northeastern, 2026-11-21.
- Concert Band Fall Concert
- Northeastern, 2026-11-22.
Tail
- What is a Scamp?
- udamonic, 2026-11-21. A small dedicated Forth computer. Filed here because it is the opposite of everything above: one language, one board, no network.
- Scientists Discover New and Horrible Eagle-Based Way Our Ancestors Died
- 404 Media, 2026-11-21.
- How 2 Security Research (MLG)
- Lobsters, 2026-11-21.
- Decapitation Seems Like a Great Way to Start X-Mas Decorating
- Hackaday, 2026-11-21.
Feed silences and verification
118 feed endpoints were polled this morning. 46 returned new content,
71 returned 304 Not Modified, and one errored.
www.bornholt.dev failed DNS resolution again. The feed has never
resolved in any recorded poll, so this is a dead endpoint rather than
an outage, and it is counted as such rather than as a silence.
Hacker News has recorded nothing since 2026-10-26. This is our bug,
not a feed silence: the endpoint answers 419 and our cache layer
records it as :not-modified, which makes it invisible in the health
report. It is unchanged from yesterday and still unfiled – bd is
not on PATH in this environment.
No arXiv announcement landed on 2026-11-21 or 2026-11-22. The cs.AI feed's newest items are dated 2026-11-20, and the same two-day gap appears at 2026-11-14/15 and 2026-11-21: it is the announcement calendar, not a selector break. Because the 14-day arXiv pool is therefore identical to yesterday's, today's eighteen papers were selected against this brief's threads – agent identity, code review, proof automation – rather than by recency, and all eighteen are new to this series.
Thirteen Slashdot URLs are published with the feed's
?utm_source=rss1.0mainlinkanon tracking parameters removed. The
paths are the warehouse paths; only the analytics suffixes are
stripped, matching the convention in previous briefs.
One of the twenty-seven new crawler-zoo arrivals carries a racial slur as its user-agent string. It is recorded in the warehouse and omitted from the list above; the count of twenty-seven includes it so the census stays accurate.
All 102 published URLs were HEAD-checked through the compliance gate
(fetch-gated, R3 blocklist then R2 robots then R4 throttle),
parallel across hosts and serial within each host. All 102 return
200 – no gate denials, no 403s, no 404s, no connection errors. The
LWN subscriber-only 403s that usually appear in this section are
absent because no [$] article is cited today.
Honoring arXiv's Crawl-delay: 15 across the eighteen abstract URLs
costs four and a half minutes on its own – serialized behind one
host, while the other thirty-seven hosts finish in parallel. Recorded
because it is the cost of the policy, not a reason to skip it.
build: 2026-11-22 | crawler-sha: b277e41 (Walsh-Research/1.2, compliance v1.3) | feeds: 118 polled, 74 publishing | items-considered: 5,523 (14d, incl. 3,272 arXiv) | warehouse: 74,267 items | published: 102 (102 URLs verified through the gate, 102 x 200, 0 x 403, 0 x 404, 0 gate denials, 0 errors)