Long thread published on X on **September 29, 2026** by **Ryan Sarver** (@rsarver), titled *"Personal AI Should Actually Be Personal"*; roughly **1,700 words**, 91.5k views at time of collection. Starting point: **Amazon** blocked **Muse** (**Meta**) from its shopping site, and users lost access to their shopping agent, *"a side effect of a dispute I had no say in."* **(A)** Definition: a personal AI must be **owned** (open source, data in controlled storage, portability), have **a single principal**, offer a readable contract and inspectable trade-offs, run wherever one chooses, and be pleasant to use. **(B)** Observation on the current landscape: Muse opts users into training by default, **Instinct** carries a *"perpetual and irrevocable"* license; estimated cost gap of **$3,000 to $7,000 per user per year** against $20 a month. **(C)** A reversal: the owned stack can end up better, because the user gives it *"every corner of your life."* **(D)** A five-layer stack (clients, harness and connectors, memory, two-tier models, machine) and a call to build a productized version of **OpenClaw**. Responds to **Brad Gerstner** on trust; extends the body of work on shopping agents and markdown memory.
#personal AI#personal AI#personal agent
Ryan Sarver (@rsarver) · auteur du fil sur X ; fonction non indiquée dans le texte.
Long-form article published on **September 14, 2026** on the X account **@GoogleCloudTech** (~2,000 words, four steps, six blocks of commands and configuration), signed by **Alan Blount**, Technical Solutions Consultant at Google. Starting point: a trivial question, handed to a research agent, billed at **$38**. The article proposes running **Claude Fable 5.1** and **Gemini 3.8 Flash** side by side behind the same **Gemini Enterprise Agent Platform** API (formerly Vertex AI). **(1) Configuration**: access to Fable is subject to Google Cloud's *Advanced AI Safety Addendum*, which requires a `setPublisherModelConfig` call with prompt-response sharing enabled for Anthropic, on pain of a 403; Flash works as soon as it is enabled. **(2) In-house benchmark** with promptfoo driving opencode on two tasks: on a git branch state, Flash answers in **1.1 s** for under a tenth of a cent while Fable costs **23 times more**; on a Postgres-to-Spanner migration, Fable produces in **12 s** a formal DAG with clock-drift risks and a rollback gate, whereas Flash delivers a linear sequence in 3 s. **(3) Usage**: *« asymmetric coordination »* — the fast model as first-line coordinator, the deep planner at checkpoints, an `ask_for_help` tool for escalation, and a warning against dynamic routers: *« Keep it boring »*. **(4) Token ROI**: the value of human time, shipped features, and incidents avoided, minus the cost of tokens and the team's ramp-up. The same task-boundary routing move as [[mazmanov-portal-spotify-shunt-claude-code-tokens-2026-09-03]], within the FinOps framework set out by [[rafal-wenvision-tokenomics-foundation-finops-ia-2026-06-04]].
#model routing#asymmetric coordination#tokenomics
Alan Blount (Technical Solutions Consultant, Google Cloud, @zeroasterisk) · publié sur le compte X @GoogleCloudTech.
Engineering post from **Spotify** published on **September 3, 2026** on engineering.atspotify.com (~1,600 words, nine sections, two YAML manifests, four command-line examples), authored by **Dimitri Mazmanov**, Principal Product Manager. It describes a personal setup designed to move I/O tasks out of the context of **Claude Code**. The premise stated upfront: *« Most of what an AI coding agent does for me isn't thinking. It's I/O »* — reading five files to answer a question about a single method, producing a test modeled on the other twenty in the directory. **(A) The modes.** **Portal by Spotify** exposes *AiKA Modes*, declarative agents on an ephemeral runtime — instructions, model, temperature, **MCP** tools — compared to *« AWS Lambda, but for agents »*; two public modes, `bulk-reader` and `code-writer`, run here on **Gemini 2.5 Flash**. **(B) The routing.** A Claude Code plugin named `shunt` replaces `CLAUDE.md` rules deemed *« advisory, not enforced »* with three layers: `PreToolUse` hooks that block any read beyond **350 lines** (threshold adjustable via `SHUNT_MIN_LINES`), two bash scripts calling the Portal CLI, two skills that provide the invocation syntax. The corpus goes to the secondary model and **never enters Claude's context**. **(C) Measurements and their limits.** On a Java monorepo, four scenarios, the reported average saving is **~90%** on `bulk-read`; the author notes that the `code-write` scenario is *« harder to measure »*, and lists three limitations — non-delegable editing, non-delegable reasoning, **10 to 30 seconds** of latency per call. Extends the budget questions from [[gupta-token-budget-wars-marginal-token-utility-2026-05-28]] and the delegation examined in [[willison-fable-judgement-delegation-subagents-2026-07-03]].
#Portal by Spotify#AiKA Modes#shunt
Dimitri Mazmanov (Principal Product Manager, Spotify) · sur le blog d'ingénierie engineering.atspotify.com.
Blog post by **Pasquale Pillitteri** (software engineer, Palermo) published on **May 29, 2026** (FR version), 18-minute read, *Claude Code & Anthropic* section. **Pivot thesis**: *« Claude Opus 4.8 is the most powerful SEO model of 2026, but almost everyone uses it wrong »* — not a model problem but a **system** problem. The golden rule: ***« strategy is a whiteboard, production is an assembly line »*** — SEO must be **split into two distinct phases**, and mixing them is *« the fastest way to waste a model that costs five dollars per million input tokens and twenty-five for output »*. **Model context**: Opus 4.8 released on **May 28, 2026** (41 days after Opus 4.7), **1M-token** context, **GraphWalks Long-Context F1 at 1M: 40.3% → 68.1%**, **SWE-bench Verified 88.6%**, **USAMO 2026 96.7%** (+27.4 pts), **HLE with tool 57.9%**, unchanged price **$5/$25** per M tokens, **Fast Mode 2.5× at $10/$50**, four **effort levels** (Low, High, Extra, Max). **The central anti-pattern** = *« the giant conversation »* / **context drift**: mixing strategy, keyword research, competitive analysis and writing in a single chat produces a *« mush of contradictory intentions »* → the model slides toward **generic best practices** ("holistic optimization", "strategic approach") instead of data-anchored content. **Phase 1 — Strategy (whiteboard, visual UI, one-off)**: dashboard / Google Sheet / Claude.ai canvas to decide while looking at the data together. **3 plays**: (a) **classified keyword research** (table of volume / difficulty 0-100 / intent / business potential / priority = volume÷difficulty×business weight); (b) **visual competitive analysis** (topic-coverage matrix, gaps); (c) **phased roadmap** (quick wins M1-2 / medium term M3-6 / pillar pages M7-12). **Extra/Max** mode is justified here (*« one right strategic decision is worth a thousand well-written pages on the wrong keywords »*). 3 closed artifacts saved to Notion/Drive. **Phase 2 — Production (assembly line, Opus 4.8 + MCP)**: the model shifts from strategist to **execution machine**; every decision **anchored to live data** via the **Model Context Protocol**. **Minimum MCP stack**: **GSC MCP** (AminForou/mcp-gsc, 500+ stars), **official Ahrefs MCP** (98 stars), **GA4 MCP**; the `modelcontextprotocol/servers` repo = **86,440 stars**, **10,000+ active servers**, 97M SDK downloads/month. Setup ~35 min, monthly refresh ~20 min. **Weekly loop**: a single prompt pulls live data, builds the brief (top 10 SERP + GSC + Ahrefs), derives H2/H3, writes, checks density, suggests titles → **+45% productivity**, draft in **6-12 min** (explicit reference to **Ryan Law / Ahrefs content engineering**, 23 skills). Mentions Anthropic's **Dynamic Workflows** (up to 1,000 subagents). **4 common mistakes**: (1) not checking the numbers (spot-check mandatory, *trust & verify*); (2) fully replacing Semrush/Ahrefs (MCP is a **layer on top**, not a substitute); (3) ignoring the **paid-organic content gap** (education client case: **2,742 wasted terms / 351 opportunities** identified in 90 s); (4) using Opus 4.8 where **Haiku 4.5** suffices (meta descriptions, alt text). **Cost**: $1-3 per 2,500-word article. **Sonnet 4.6** suffices for recurring production, Opus 4.8 reserved for strategy. SEO-optimized and self-referential article (the author writes about SEO in content itself designed to rank for "Opus 4.8 SEO"). Direct convergence with **Ryan Law/Ahrefs** (cited), **systems around the model** (Dropbox/Okumura), **skills-over-prompts** (Lattice), Haiku/Sonnet/Opus model routing (Gupta token-to-outcome).
#Claude Opus 4.8#AI SEO#two-phase workflow
**Pasquale Pillitteri** — Ingénieur informatique / développeur logiciel basé à **Palerme** (Italie) · certifié Innovation Manager UNI 11814:2021. Auteur d'un blog tech actif (rubrique *Claude Code & Anthropic*) · avec une newsletter hebdomadaire (~3,4k lecteurs). Article publié en version **FR** le **29 mai 2026** (lendemain de la sortie d'Opus 4.8).