# Claude defaults sessions to auto mode, Grok Bot reaches phone apps and 1Password, Claude Models GA on Google Cloud Date: 2026-10-23 Language: en Canonical: https://code-echo.pages.dev/2026/10/23/ai-twitter-hots-en --- # AI Twitter/X Hots Digest · 2026-10-23 (Friday) ## Today's highlights 1. **Claude defaults to auto mode across clients**: Starting next week, Pro/Max/Team sessions on web, desktop, and mobile stop asking for step-by-step approval; automated checks block risky actions. Quoted prior testing: classifiers caught ~**89%** of dangerous commands vs ~**14%** with manual approval. 2. **Grok Bot reaches phone apps and 1Password**: Calendar, Reminders, Contacts on iOS/Android, plus approved 1Password logins — the personal-agent race heats up again. 3. **Claude GA on Google Cloud, formal verification, and Skills donation**: Enterprises can buy Claude with GCP IAM/billing; Frontier Red Team verified **100+** OSS libs with Claude; Agent Skills go to the Agentic AI Foundation. --- ## 1. Claude: auto mode by default on web, desktop, and mobile **Key points**: @claudeai says that starting next week, sessions across Claude **web, desktop, and mobile** will run in **auto mode by default** on **Pro, Max, and Team** plans: instead of approving each step, an automated check blocks risky actions, and you can switch back to manual anytime (~9.8k likes). The post quotes earlier Claude Code testing where auto-mode classifiers caught about **89%** of dangerous commands versus about **14%** with manual approval. Community roundups put the change under “fewer interruptions,” now pushed from CLI to every client. **Why it matters**: After Claude Code made auto mode the default, the same classifier-backed pattern lands in everyday chat sessions — smoother workflows, rewritten safety boundaries. - claudeai: auto mode default across clients: https://x.com/claudeai/status/2113360845409583307 - husker_eth: included in the day's tape: https://x.com/husker_eth/status/2113389229292281924 ![Claude auto mode default across clients](/images/twitter-hots/2026-10-23/01-claude-auto-mode.jpg) --- ## 2. Grok Bot: native phone apps + 1Password **Key points**: @bot shipped two product updates in a row. One: Grok Bot can use **Calendar, Reminders, Contacts**, and more apps on your phone, rolling out on iOS and Android (~4.7k likes). Earlier: it can use your **1Password** account — approve the logins you want to share, and Bot signs in for you over the next few days (~6k likes, 1k+ bookmarks). @elonmusk amplified with “Try Grok @Bot”; @poteto highlighted the native phone-app angle. **Why it matters**: Personal agents move another layer down — into system apps and password vaults — as Claude Duet / Muse / Dots keep competing on always-on agents. - bot: phone Calendar / Reminders / Contacts: https://x.com/bot/status/2113393684209176718 - bot: 1Password integration: https://x.com/bot/status/2113332983226831339 - elonmusk: Try Grok @Bot: https://x.com/elonmusk/status/2113329537509449744 - poteto: use native phone apps: https://x.com/poteto/status/2113411672815944075 ![Grok Bot phone apps](/images/twitter-hots/2026-10-23/02-grok-bot.jpg) --- ## 3. Claude Models on Google Cloud generally available **Key points**: @claudeai announced **Claude Models on Google Cloud (Anthropic managed)** is now **generally available**: full Claude Platform features on Google Cloud with GCP IAM credentials, billing, and commitment retirement (~2.4k likes). The follow-up says new features and betas ship the same day as on the native Claude Platform — including **Opus 5.5 fast mode, code execution, and the Skills API**. **Why it matters**: Clearer enterprise path — buy Claude against existing GCP commitments without waiting for platform parity. - claudeai: Claude on Google Cloud GA: https://x.com/claudeai/status/2113380122468454765 - claudeai: Opus 5.5 fast mode / Skills API same day: https://x.com/claudeai/status/2113380126561800305 ![Claude Models on Google Cloud GA](/images/twitter-hots/2026-10-23/03-claude-gcp.jpg) --- ## 4. Anthropic: formal verification of OSS libs at scale with Claude **Key points**: @AnthropicAI’s Frontier Red Team blog: formal verification can prove code is free of certain bugs, but historically only worked for small codebases or heavy expert time. With **@theoremlabs**, they used Claude to prove security properties in **100+** real-world open-source libraries over a few weeks (~2.3k likes, nearly 1k bookmarks), and published the research. **Why it matters**: AI is not only finding bugs — it is pushing “prove the absence of a class of bugs” to real scale, a counterpoint to yesterday’s PHP2Shell “AI finds RCE” story. - AnthropicAI: formal verification research: https://x.com/AnthropicAI/status/2113390212911083894 ![Anthropic formal verification](/images/twitter-hots/2026-10-23/04-anthropic-formal-verify.jpg) --- ## 5. Agent Skills donated to the Agentic AI Foundation **Key points**: @bcherny says **Agent Skills** started as an experiment in Claude Code; after broad industry adoption, Anthropic donated it to **@AgenticAIFdn**, next to MCP (~1.3k likes). The quoted @ClaudeDevs post is more concrete: since December 2025, **70+** agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code (~5.6k likes). **Why it matters**: Portable “skills” for coding agents move from one product’s experiment to foundation governance — affecting Claude Code and competing harnesses alike. - bcherny: Skills donated to the foundation: https://x.com/bcherny/status/2113333859907747871 - ClaudeDevs: donation note and 70+ platforms: https://x.com/ClaudeDevs/status/2113328526413996100 ![Agent Skills donation](/images/twitter-hots/2026-10-23/05-agent-skills.jpg) --- ## 6. AI tooling security week: Devin’s open-source security plugin, PHP2Shell / LiteLLM aftermath **Key points**: @cognition open-sourced **Vulnerability Fixes**, an agent plugin for recent PHP and Node.js remote-code-execution issues: it helps Devin or any coding agent find affected repos, ask before changing anything, patch to a verified fixed version, test before and after, and open one focused PR per repo (~200 likes). @jeffwang adds that after a big day of PHP / Node / GitLab disclosures and incidents, they open-sourced the plugin and are giving Enterprise users credits to focus on remediation; Devin’s edge is validating that the rest of the app still works after the change. PHP2Shell, the LiteLLM **1.107.0** supply-chain malware, and Railway env-var issues still show up in community briefs, but those launches were yesterday’s main story — noted here only as continuing context. **Why it matters**: Once agents hold shells and secrets, patching becomes an agent workflow; open plugins standardize the fix loop. - cognition: Vulnerability Fixes plugin: https://x.com/cognition/status/2113356319751119359 - jeffwang: open-source note and Enterprise credits: https://x.com/jeffwang/status/2113356319163875612 - testingcatalog: daily brief continuing PHP2Shell etc.: https://x.com/testingcatalog/status/2113184364209004811 - Austen: LiteLLM 1.107.0 = malware, rotate keys: https://x.com/Austen/status/2113229764383105255 ![Devin Vulnerability Fixes plugin](/images/twitter-hots/2026-10-23/06-devin-plugin.jpg) --- ## 7. T3 Code: smooth on weak networks + noEmDashCopy lint **Key points**: @theo says he often didn’t notice degraded internet because **T3 Code** kept running flawlessly (~370 likes). Separately, he took a copy regression seriously: after someone spotted an em dash, he added a **noEmDashCopy** lint so it doesn’t happen again (~630 likes). **Why it matters**: T3 Code as a Claude Code harness / orchestration layer remains a high-engagement coding product on the timeline; UX details (weak-net smoothness, copy lint) are part of the pitch. - theo: still smooth on weak networks: https://x.com/theo/status/2113351683007025378 - theo: noEmDashCopy lint: https://x.com/theo/status/2113369404994130299 ![T3 Code noEmDashCopy](/images/twitter-hots/2026-10-23/07-t3-code.jpg) --- ## 8. Gemini 4 Argon: official 3D agent demo vs coding skepticism **Key points**: @Google showed **Gemini 4 Argon** starting from a single **Nano Banana** image, driving **Blender MCP** in an autonomous loop inside **@antigravity** to build a finished audio-reactive 3D cathedral — sculpting Gothic architecture, aligning camera grids, staging dynamic lighting. Meanwhile @NerdSnipePod and others keep asking why anyone would use Argon for coding; the gap between multimodal demos and coding trust is still loud in podcasts and replies. **Why it matters**: Multimodal agent demos look strong; coding credibility is not settled — a clean “model vs coding scenario” contrast. - Google: Argon + Antigravity + Blender MCP: https://x.com/Google/status/2113353489938075794 - NerdSnipePod: skepticism about Argon: https://x.com/NerdSnipePod/status/2113125534120984773 ![Gemini 4 Argon cathedral demo](/images/twitter-hots/2026-10-23/08-gemini-argon.jpg) --- ## 9. DeepSeek V4.1 Flash: 100+ tok/s on Mac + OpenClaw **Key points**: @NFT_Chen ran **DeepSeek-V4.1-Flash-1017** on a single **Mac M5 Ultra** (80-core GPU + 256GB) via **mlx-serve**: stable **102–112 tok/s**, peak **136.7**, prefill ~**1770 tok/s**, 3-bit quant, wireable from Claude Code / Codex to a local port. @openclaw announced the model is available in OpenClaw and asked for agent feedback. **Why it matters**: For open weights in coding / agent land, the questions remain “how fast locally” and “which harness picks it up.” - NFT_Chen: 100+ tok/s on Mac: https://x.com/NFT_Chen/status/2113288264706826303 - openclaw: available in OpenClaw: https://x.com/openclaw/status/2113414141327380480 ![DeepSeek V4.1 Flash local throughput](/images/twitter-hots/2026-10-23/09-deepseek-flash.jpg) --- ## 10. Reflection Beam + Cline: free 501B and an OpenCode demo **Key points**: @cline added new free models including **Reflection Beam (501B)** and Nemotron 3.5 Super VL (120B), noting that six months ago these Terminal-Bench scores were frontier — open weights make them more accessible. @reflection_ai plugged Beam into **@opencode**, asked it to study Unsloth and the latest smallest Gemma-4, and build a Text2SQL fine-tuning notebook — out of distribution for Beam — and raised heldout accuracy by about **66.5%**. **Why it matters**: Open MoEs move from “downloadable” into the default free menu of everyday coding agents (Cline / OpenCode). - cline: Beam 501B and other free models: https://x.com/cline/status/2113356814322651618 - reflection_ai: Beam × OpenCode Text2SQL: https://x.com/reflection_ai/status/2113387780676206627 ![Cline free Reflection Beam](/images/twitter-hots/2026-10-23/10-beam-cline.jpg)