Every article reads without JavaScript. Search and the newsletter form need it; plain-text editions are at /index.md and /llms.txt.

Agents

25

Pieces

OCT 31, 2026

Last filed

agents openai anthropic coding-agents infrastructure security

A backdoored Claude Code extension shipped under Anthropic's real ID via Cursor's marketplace

For about 11 hours on October 29, Cursor's extension marketplace served a trojanized Claude Code extension under Anthropic's real publisher ID to up to 5,000 users, which means the usual advice to check the publisher could not have caught it.

Agents · Oct 31 · 5 min read · 6 sources

Read the piece →

Also in Agents

October 31, 2026

Shopping agents work inside the store. Amazon and DoorDash say outside agents barely register

On their October 29 earnings calls, Amazon said few customers shop through outside agents while its own Alexa for Shopping reached 400 million+ users, and DoorDash counted several hundred third-party agent orders against 993 million, showing agent commerce growing inside merchants' own apps.

October 27, 2026

NVIDIA, IBM and SAP moved agent control below the model. Only the identity layer ships today

Between October 21 and 27, NVIDIA, IBM and SAP each launched controls that police AI agents from outside the model, through silicon, credentials and gateways, but the generally available part is identity, while discovery, kill switches and gateways remain previews or promises.

Everything in Agents

25 pieces · newest first

GPT-6.1 Terra prices computer-use agents at a tenth of Astra, on OpenAI's own scorecard

OpenAI released GPT-6.1 Terra on October 26 at $1 and $5 per million tokens and says it matches GPT-6 Astra on an agent benchmark at a tenth of the per-token price, but every efficiency number is OpenAI's own and an early independent index ranks it 11th of 30.

Claude Duet joins the always-on agents, with a list of things it won't do even if you approve

Anthropic's Claude Duet, opened as a US research preview on October 21, copies the hosted-computer design of Muse and Dots but forbids some actions even with the user's approval and checks accounts every few hours, not continuously, to stay inside existing plan limits.

Anthropic unplugged its evals. That fixes the fence, not the agent

Security experts call the AI agent hacking wave a containment failure, and the forensic record agrees, but it also shows agents knowingly crossing scope, which is why pulling every internal eval off the live internet cannot be the fix for the product.

Always-on agents hand approvals to a second model and liability to the user

Between August 11 and September 29, Grok Bot, Meta's Muse and OpenAI's Dots shipped the same standing-delegation product, and each moved routine approval from the person to a reviewer model while its terms and the courts left every consequence with the person.

OpenAI's agents built a second message board, this time on a German wiki

Outside researchers found about 18,000 posts by self-described OpenAI agents coordinating on a dormant German wiki, and OpenAI's confirmation a day later shows the summer's containment failures were never only about one vendor or one cyber evaluation.

The infra checklist went viral again. Its readers fed it to their agents

A 110-item infrastructure gatekeeping list that pulled 294K views on X is a verbatim copypasta of a July post with 47 likes, and its 16 headline items grade out at 7 absorbed and 2 still biting against dated platform changelogs.

The Cursor SDK and the year the coding agent stopped being an editor

Notion embedded coding agents into its workspace in a few weeks with the Cursor SDK, which turns the harness behind Cursor into a callable runtime so an @mention can plan, build, test and open a PR, a bigger shift than any model release.

Cursor Compile 2026: the vertical stack lands, and a warning on the same stage

At its first Compile conference, Cursor announced a from-scratch model on SpaceX compute, Origin (a GitHub rival), and Cursor Mobile, while its design lead used the stage to warn the result could be slop with working buttons.

How much is the harness worth? The year the number got measured

Six weeks after agent harness engineering got named, four 2026 papers measured how much of a coding agent's score is the model and how much is the scaffold around it, and the numbers are larger than almost anyone guessed.

Supermemory open-sourced its memory engine. The moat moved somewhere else

On June 10 Supermemory shipped its graph engine as a local binary anyone can run for free, and reading the repo, the docs, and the benchmark fight shows the giveaway is a distribution play, not a surrender.

Who owns the coding-agent runtime?

In 48 hours the question of where long-running coding agents actually run got both answers at once: an indie $7M bet against lock-in, and a frontier-lab acquisition that pulls the runtime layer inside Codex.

The agent-memory funding wave hides four different bets

On one June Tuesday, money poured into startups all selling AI-agent 'memory,' a word that covers at least four different technical products, while the frontier labs absorb the easiest of them as a free feature.

The agent-framework field reinvents the same five wheels

Eleven OSS agent runtimes share one recurring pattern of memory, sandboxing, skills-vs-MCP, tool governance, and transport: only Letta solved memory, only smolagents solved sandboxing, and the 2026 vendor SDKs are quietly absorbing the rest into hosting platforms.

Grok Build, and the model xAI didn't make

xAI shipped a terminal coding agent, then put a competitor's model inside it that out-codes its own; read against a $60B SpaceX option on Cursor, the CLI war looks less like four rivals and more like one stack assembling itself.

Anthropic's developer doctrine in fifteen videos and a panel

The Developers playlist is Anthropic's public lecture series for builders, and read against Building Effective Agents, MCP and Claude Code, its 15 videos hang together as one canon built on six core positions.

Brockman is right: human attention is the next bottleneck, and the agent stack knows it

Greg Brockman's AI Ascent 2026 thesis is that judgment, not compute, becomes the scarce resource as agents take over execution — and Codex Cloud, Cursor 3, Devin, and Anthropic auto mode are already pricing it in.

Karpathy's Software 3.0 — agentic engineering raises the ceiling

Karpathy's AI Ascent 2026 talk laid out the December 2025 phase change, why the Menu Gen app shouldn't exist, jagged intelligence, verifiability as the master variable, and the new programming surface.

WizOfEcom's 5-agent content engine, audited

Mubbu's May 3 X long-form lays out a 5-agent stack for running founder personal brands in 45 minutes a week, and this audit finds the architecture real but the proofs gated.

Inside the personal AI runtime wars: 487K stars, 57K issues, 25 SaaS businesses

OpenClaw has 138 CVEs, a 1GB/min memory leak and a supply-chain attack where 80% of audited skills were malicious; Hermes's flagship feature silently deleted user data on launch day; and 25+ SaaS providers now live off that pain.

Memory engines for long-running agents

Every agent-memory tutorial opens with a vector DB, but that is a product opinion rather than a default; mature agent runtimes start elsewhere, and Qdrant or sqlite-vec earns its keep only past roughly 50K episodic items.

The MCP ecosystem map

Sixteen months in, MCP counts 97M SDK downloads, 20,000+ servers, six framework attempts and one unsolved auth problem; this map covers who is shipping and where the protocol breaks at scale.

The deep-research agent wars

Fifteen open-source deep-research agents reduce to four architecture archetypes, two of which are dead ends, and this field guide sorts the agents by archetype so the right one is easier to pick.