Radar, November 21, 2026: ten signals from X on Inkling 2 Mini, Claude Code 2.1.330 and Browser Run
In short: The key signal of November 21: Thinking Machines released Inkling 2 Mini, an open model that runs on a Mac. Alongside it, ten short signals on easel in Claude Code 2.1.330, new formats in Cloudflare Browser Run, the Riemann claim, Cursor and Grok Build, Perplexity Computer and OpenAI, each with its source on X.

Illustration: AI-generated (OpenAI image model via Codex): a radar screen with ten signals.
1.Inkling 2 Mini: a 26.4-billion-parameter open model for your Mac
Confidence: high (blog, model card and Ollama page read; scores from the maker)Thinking Machines released Inkling 2 Mini under Apache 2.0 on November 20. The model is about 20 GB, runs on a Mac with 32 GB or more and loops its middle layers three times per token. The maker reports 79.2 percent on SWE-bench Verified. It is on Hugging Face and in Ollama 0.40.17 (pre-release).
Source on X: @thinkymachines · @ollama · Thinking Machines, aankondiging
Read also: Inkling 2 Mini locally · Inkling 2 Small
2.Claude Code 2.1.330 draws charts with easel
Confidence: high (release notes 2.1.327 to 2.1.330 read)Version 2.1.330 of November 20 adds easel, a built-in mod that draws charts on request and under MCP metrics. Scheduled tasks and /loop can now run for 30 days instead of 7. Earlier this week came onFailure: block for MCP hooks (2.1.328) and a fix for a reset ~/.claude.json (2.1.329).
Source on X: @alexmichael · @ClaudeCodeLog · GitHub, release-notes v2.1.330
Read also: Claude Code 2.1.330 and easel · Claude Code 2.1.326
3.Cloudflare Browser Run: /snapshot also returns PDF, links, scrape and JSON
Confidence: high (changelog read; not tested by us)Since November 19, /snapshot also returns a PDF, the links, selected elements and Workers AI-extracted JSON from a single page load. At least two formats are needed; if one fails, the whole request fails. The JSON format counts toward Workers AI usage.
Source on X: @CloudflareDev · Cloudflare-changelog
Context in the briefing: Agents in the browser in the November 21 briefing
Read also: Browser Run /snapshot
4.Riemann hypothesis with Claude: a claim still under review
Confidence: low (X only, verification under way)Accounts on X report that a mathematician at Anthropic found a proof of the Riemann hypothesis together with Claude, with Lean code online. Independent verification is still under way. We did not open the website or the code. Treat it as a claim, not a result.
Source on X: @kimmonismus · @Relox_AI
Context in the briefing: The Riemann claim in the November 21 briefing
5.Rumour: Cursor to be renamed Grok Build
Confidence: low (leak from one account, unconfirmed)@GrokInsider and @blankspeaker report that internal Cursor builds have been renamed and that the Cursor CLI contains code that downloads Grok Build 2.0 (Unified). There is no official word from Cursor or xAI. If you have scripts that call cursor, wait for an announcement before changing them.
Source on X: @GrokInsider · @blankspeaker
Context in the briefing: Cursor and Grok Build in the November 21 briefing
Read also: Grok Build
6.Hermes hackathon wraps up, Microsoft also builds on OpenClaw
Confidence: medium (official accounts; not checked further)Nous Research announced the winners of its Plugin Hackathon, which drew almost a thousand entries. @openclaw says Microsoft contributes to OpenClaw and provides maintainers. Read the code of community plugins before installing them.
Source on X: @NousResearch · @openclaw
Context in the briefing: Hermes and OpenClaw in the November 21 briefing
Read also: Hermes Enterprise in Teams · OpenClaw 2026.11.4
7.Perplexity Computer works as an extension in Chromium browsers
Confidence: medium (official account; not tested)From the side panel you hand Computer a task that it carries out across your tabs and tools. Preferably use a separate browser profile without sensitive sessions. @AravSrinivas also mentions a Mac app with local models; we have not seen it.
Source on X: @perplexity_ai · @AravSrinivas
Context in the briefing: Perplexity Computer in the November 21 briefing
Read also: Perplexity Brain and skills · Perplexity Teammates
8.OpenAI publishes research on detecting distillation
Confidence: medium (official account; research paper not read by us)OpenAI describes how capabilities transfer between models and how it detects coordinated attempts to copy its models from their outputs. The post names no concrete rules for API users. Also new: MedChemBench, a benchmark for medicinal chemistry.
Source on X: @OpenAI · @OpenAI over MedChemBench
Context in the briefing: OpenAI in the November 21 briefing
Read also: Misuse detection at the labs · GPT-Live-1.1 in the API
9.Grok Bot connects to QuickBooks, US only
Confidence: medium (official account; not tested)Grok Bot can pull cash flow from QuickBooks and draft invoices, quotes and reminders that you approve yourself. The integration only works in the United States. Check which permissions you grant it.
Source on X: @bot
Context in the briefing: Agents in the browser in the November 21 briefing
10.Warning: do not paste images with instructions into an agent
Confidence: low (single posts without a primary source)Accounts urge users to paste images with instructions into Grok Bot for trading bots; that is a known route for prompt injection. Another account claims Grok Bot's source code has leaked; that is unverified. Do not open leaked code or paste anything of unknown origin.
Source on X: @RohOnChain · @choopyplug1
Context in the briefing: Unconfirmed in the November 21 briefing


