Internal research report dated **August 12, 2026** consolidating, for presentation purposes, everything publicly documented about **Buzz** — **Block**'s humans + agents workspace, launched on **July 21, 2026** under the **Apache 2.0** license. It aggregates the two engineering posts already filed alongside the corporate announcement, the GitHub repository, press coverage, X, and **three independent hands-on accounts** that constitute the dossier's only non-self-reported data. **(A) A vocabulary gap documented by quotation**: **Jack Dorsey**'s launch tweet announces *"model-agnostic, decentralized, self-sovereign, and open source"*; Block's `ARCHITECTURE.md` states *"The relay is the single source of truth. All reads and writes flow through it. There is no peer-to-peer event exchange, no gossip, no replication."* The relay is therefore single and authoritative per community: Buzz's "decentralization" is an **organizational sovereignty** — self-hosting and portable identity — not network redundancy. **TFTC**'s formulation: *"Two of those three hold cleanly. The third needs a qualifier."* **(B) An asymmetry between demonstrated rigor and exploitation risk.** On one side, a rare degree of formalism for a v0.4.x/0.5.x: multi-tenant isolation specification **mechanized in TLA+**, authorization properties verified in **Tamarin**, a model-checked Git storage protocol, a hash-chained append-only audit log, 127 *event kinds*, NIP-01/42/98/34. On the other, channel membership is the unit of permission — *"channel membership is not fine-grained tool authorization"* (João Queirós) —, agents run in `--dangerously-skip-permissions` outside any sandbox on a human's machine, and observability is lacking: *"Buzz tells me an agent got a message. It doesn't tell me what happens next"* (DevTools Daily, which reports silent OOM kills). Block acknowledges it: *"the agent can do anything, and security rests entirely on restricting who can tell it what to do"*. **(C) The technical stack**, absent from the filed posts: **Rust** relay (Axum WS + REST), **Postgres**, **Redis**, **S3/MinIO** via Blossom, **Tauri + React** desktop client. Agent integration goes through **`buzz-acp`**, an **ACP** harness that plugs in goose, Codex and Claude Code and translates **ACP ↔ MCP**, plus **`buzz-agent`**, an in-house agent. The report corrects itself on one point: the *"+33% more work"* in Block's TL;DR is the **ratio of completed tasks (20 versus 15 out of 44)**, not a score gain — the score itself rises from 59.1% to 71.5%, i.e. **+12.4 points**.
#Buzz#buzz.xyz#Block
**Deep Research Veille Interne** — rapport non signé · produit le **12 août 2026** en préparation d'une présentation. Aucune URL publique ; source archivée dans `raw-data/`.
A watch note by **Didier Girard** published on **X** on **August 7, 2026**, which reads the launch of **Shieldstral 1.0 3B** (Mistral AI, August 4, 2026) not as a product release but as **the production deployment of a doctrine**. Starting point: on **May 13, 2026**, before the National Assembly's commission of inquiry into digital vulnerabilities, **Arthur Mensch** refused any oversight role for Mistral over the end use of its models — *"we do not have democratic legitimacy"* — explicitly rejecting **Anthropic**'s stance. Less than three months later, Mistral releases a **moderation model**. The author dismisses the apparent contradiction: **Shieldstral carries no taxonomy of the licit and the illicit**, it answers a **question the user writes**. **The mechanism is the heart of the note**: a three-part prompt (context + severity / a single closed question / the content to be judged), a `yes` or `no` response, and the **softmax over these two tokens** produces a continuous score between 0 and 1. **The moderation policy is not in the weights, it is read at inference time** — whereas **Llama Guard 4** embeds the MLCommons taxonomy fixed at training time, Shieldstral reads yours in natural language, modifiable **without retraining**. The technical report (**arXiv:2607.25857**, July 28, 2026) quantifies the cost of this choice: fine-tuning on public data alone = **61.1% F1** on policy adaptability; **4.4 million contrastive pairs** generated by an LLM (the same content rewritten to violate a policy but not its sibling policy) = **+23.3 points**; **91.3%** after merging three checkpoints. Characteristics: **3.8B actual parameters** (the "3B" in the name rounds down), **Ministral 3** base + **Pixtral** vision encoder, **12 languages**, **16 GB of VRAM in BF16**, **Apache 2.0**. Text performance: **84.9% average F1**, on par with **GPT-OSS-Safeguard-20B** (seven times larger), ahead of **Qwen3Guard-8B** (84.0) and far ahead of **LlamaGuard-4-12B** (69.1). **A caveat raised by the author himself**: *all these figures come from Mistral, on test sets selected by Mistral, and no third-party evaluation existed as of August 6*. The note's structuring thesis is an **opposition of topologies**: at **Anthropic**, the guardrail lives **in the weights** and the publisher arbitrates who is exempt from it (**Claude Fable 5** public with safety measures / **Claude Mythos 5** without, reserved for approved cyberdefenders of **Project Glasswing**, June 9, 2026); at **Mistral**, the guardrail **sits outside the model** — a separate, open, self-hostable component, whose policy belongs to the deployer. Explicit customer alignment (ministry of the Armed Forces, BNP Paribas, French and Luxembourg government administrations). The note closes on a **setback documented in three points**: **auditability** (binary output, no reasoning trace, while the deployer inherits the burden of justification under an AI Act audit), **robustness** (the first chapter of Voltaire's *Treatise on Tolerance* classified as "calls for violence" by a tester on the Hacker News thread — a mention/endorsement confusion), **availability** (as of August 6: no billed endpoint on La Plateforme, no official Ollama). Three deployment rules to close.
#Shieldstral#Shieldstral 1.0 3B#Mistral AI
**Didier Girard** — auteur de la note · publiée sur son compte X. Écrit ici en **analyste de doctrine industrielle** plutôt qu'en testeur : il n'a pas déployé le modèle · il croise une **audition parlementaire** (Mensch, 13 mai) · un **lancement produit** (Shieldstral, 4 août) · un **rapport technique** (arXiv, 28 juillet) et un **contre-exemple concurrent** (Anthropic, 9 juin) pour montrer qu'ils forment une position cohérente. Deux marqueurs de posture : il **borne explicitement la valeur des chiffres** qu'il cite (aucune évaluation tierce) et il **termine par des règles opérationnelles** — l'analyse doit sortir avec sa traduction en décisions de déploiement.
Skill entry: **graphify** by **Safi Shamsi** (Graphify Labs, Y Combinator S26) turns an entire project — code, docs, PDFs, images, videos — into a **queryable knowledge graph**, invoked via `/graphify` from Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, and about fifteen other clients. Observed on **August 6, 2026**: **103,187 stars**, **10,024 forks**, repository created on **April 3, 2026**. Apache-2.0, Python 3.10+, default branch **v8**. **Three design choices**, stated in the README. *"Code maps for free, fully local"*: code is parsed into a **tree-sitter AST**, deterministically and without an LLM, nothing leaving the machine. *"Every edge is explained"*: each edge is labeled **`EXTRACTED`** (explicit in the source) or **`INFERRED`** (resolved by graphify), with a third value `AMBIGUOUS` appearing in the report. *"Not a vector index"*: *"no embeddings, no vector store: a real graph you traverse"*. **Three outputs**: `graph.html` (interactive graph), `GRAPH_REPORT.md` (god nodes, surprising connections, suggested questions), and `graph.json` (persistent graph, queryable weeks later without rereading the files). **Three query modes** replacing grep: `query` (subgraph for a natural-language question), `path A B` (shortest path between two entities), and `explain` (neighborhood of a concept). **Coverage**: 36 tree-sitter grammars (~40 languages), plus Terraform, Apex, MCP configurations, package manifests, Office, Google Workspace, PDFs, images, and video/audio transcribed locally by faster-whisper. Communities detected via **Leiden**, labeled without an LLM. **Benchmarks**: on LOCOMO, recall@10 of **0.497** versus 0.149 for supermemory and 0.048 for mem0, but lower QA accuracy (45.3% versus 49.7%); on LongMemEval-S, **76%**, on par with a dense RAG; and *"Graph build — LLM credits: 0"*. **Points to record**: the `main` branch carries a v1-era README describing a different product (Claude Code-only skill, the "71.5× fewer tokens" claim); the PyPI package is named **`graphifyy`** with two *y*s, while the `graphify` name is being reclaimed; and a **query log** is written by default to `~/.cache/graphify-queries.log`, which can be disabled via an environment variable.
#skill#knowledge graph#knowledge graph
**Safi Shamsi** — créateur et mainteneur de graphify · et de **Graphify Labs** · société passée par **Y Combinator (promotion S26)** selon le badge du dépôt. Il maintient aussi le site d'annuaire `graphify.net` (cf. [[graphify-net-annuaire-ia-coding-2026-08-06]]) et publie un livre · *The Memory Layer* · sur les idées et l'architecture derrière le projet.
**Zed** blog post signed by **Franciska Dethlefsen** (head of growth and marketing), published on **May 14, 2026** — the day after Anthropic's announcement — to answer Zed users' questions. **Subject**: starting **June 15**, Anthropic **splits Claude subscription billing into two pools** — one for its **first-party tools** (chat, the official Claude Code CLI), the other for **third-party agent and SDK usage** (anything going through **ACP**, `claude -p`, or a third-party tool). Usage via ACP **then stops drawing from the Pro or Max limits** and switches to a monthly **"Agent SDK" credit**: **$20 for Pro, $100 for Max 5x, $200 for Max 20x**. Once the credit is exhausted, usage continues **at standard API pricing** if overage is enabled — otherwise requests stop until the next cycle. **The figure driving the article**: subscriptions had until then subsidized agentic usage by a factor of **≈15 to 30×** relative to API pricing, and the new credits are billed **at full API rates** — hence *« for anyone using agents heavily, this is a major cost increase »*. **Three options are proposed**, in an order that reveals Zed's position: (1) keep the subscription by running the **official `claude` CLI in a terminal inside Zed** rather than via ACP — *« when the official claude CLI runs in the terminal, it uses your subscription's limits, not the new credit »*; (2) use Zed's built-in agent with the provider of one's choice (Zed-hosted models, API keys, Copilot, local Ollama, DeepSeek); (3) plug in **any ACP agent** — OpenCode, Codex, Factory, Cursor —, several of which still offer rate-limited subscriptions that subsidize heavy usage. **The underlying thesis**, and the real reason for the post: *« ACP is an open protocol… so that your editor is never locked into one provider's pricing decisions »*, with the explicit anticipation that *« this kind of change won't be the last »*. **The post carries an addendum dated June 16, 2026** announcing that **the change is suspended**: ACP, `claude -p`, the Agent SDK, and third-party applications continue to work with subscriptions **as before**, no separate credit to claim, limits unchanged, Anthropic revising its plan with advance notice announced. **The artifact is thus self-contradicting**: its most important content — the reversal — postdates its own publication date by a month.
#Zed#Anthropic#Claude subscription
**Franciska Dethlefsen** — head of growth and marketing chez **Zed Industries**. Le rôle est déterminant pour lire le texte : ce n'est pas un billet d'ingénierie mais une **communication de crise produit** · écrite le lendemain d'une annonce d'un fournisseur dont Zed dépend · à destination d'utilisateurs inquiets. La signature growth/marketing explique la structure (problème → options → réassurance) et le fait que l'argument protocolaire arrive en conclusion plutôt qu'en tête.