Behavioral differences from Claude Opus 5 and the prompting and harness patterns that address them: effort calibration, thinking behavior in API integrations and chat, progress updates, unattended and multiagent tasks, safeguard refusals, frontend design, complex visual inputs, multi-app workflows, and pasted text in user messages.
Beautiful UI — Crafted primitives for AI-native interfaces
A small library of extremely crafted, copy-paste components for chat agents, thinking states, human-in-the-loop approvals, and everything agents need to talk to humans beautifully.
How Claude marks AI-generated content | Claude Help Center
Anthropic has signed the EU AI Act's Article 50(2) Code of Practice on Transparency of AI-Generated Content, as a provider of both generative AI models and generative AI systems. This article describes how we’re planning to put those commitments into practice, how marking works, and what its limitations are. We’ll update this article and publish more detailed technical guidance as it becomes available.
Auto mode for Claude Code
Really interesting new development in Claude Code today as an alternative to --dangerously-skip-permissions: Today, we're introducing auto mode, a new permissions mode in Claude Code where Claude makes permission decisions …
The peril of laziness lost | The Observation Deck
In his classic Programming Perl — affectionately known to a generation of technologists as "the Camel Book" — Larry Wall famously wrote of the three virtues of a programmer as laziness, impatience, and hubris: If we’re going to talk about good software design, we have to talk about Laziness, Impatience, and Hubris, the basis of good software design. We’ve all fallen into the trap of using cut-and-paste when we should have defined a higher-level abstraction, if only just a loop or subroutine. To be sure, some folks have gone to the opposite extreme of defining ever-growing mounds of higher level abstractions when they should have used cut-and-paste. Generally, though, most of us need to think about using more abstraction rather than less.
Cognition | Agent Trace: Capturing the Context Graph of Code
We’re excited to join in Cursor, Cloudflare, Vercel, git-ai, OpenCode and others in support of [Agent Trace](https://agent-trace.dev/). As described in the spec, Agent Trace is an open, vendor-neutral spec for recording AI contributions alongside human authorship in version-controlled codebases.
Frontend Minimalism in Action: Do More With Less JavaScript | Peter Kröner | webinale Berlin 2026
Michael R. Crusoe (@biocrusoe@fairpoints.social)
Oh, I like this part > No AI-generated text in human-to-human communication > When our maintainers volunteer their time to review your issue, PR, or proposal, they do not want to talk to a machine. This is a basic principle of respect. https://mastodon.gamedev.place/@godotengine/116839550229253906
Machine-readable attitudes - Computational Semantics++
User intent declarations can be viewed as propositional attitudes (permission, prohibition, desire, intention, belief, etc.) over structured descriptions of data use. Treating them that way gives you composable building blocks from existing theory and lens-based translations between community vocabularies that make explicit what each translation cannot carry through.
Agentics: Memorizing Session Transcripts Isn't Useful
Keep track of artifacts, not scratch. Alt title: Claude, please stop trying to memorize random crap
Impeccable: Design skills for AI harnesses
1 skill, 23 commands, and curated anti-patterns for impeccable frontend design. Works with Cursor, Claude Code, GitHub Copilot, Gemini CLI, and Codex CLI.
Impeccable: Design skills for AI harnesses
1 skill, 23 commands, and curated anti-patterns for impeccable frontend design. Works with Cursor, Claude Code, GitHub Copilot, Gemini CLI, and Codex CLI.
I work, I think? - Annotated
How AI may quietly dismantle the feedback loop that turns inexperienced people into competent ones, and why my work matters to me.
Why the fuss about conversational programming?
First, there isn’t much fuss … yet. But there will be.
Impeccable: Design skills for AI harnesses
1 skill, 23 commands, and curated anti-patterns for impeccable frontend design. Works with Cursor, Claude Code, Gemini CLI, and Codex CLI.
Anthropic extends MCP with a UI framework
Anthropic is turning Claude into an app platform, with interactive widgets from Slack, Figma, Asana, and others.
Background Coding Agents: Context Engineering (Honk, Part 2) | Spotify Engineering
This is part 2 in our series about Spotify's journey with background coding agents (internal codename: “Honk”) and the future of large-scale software maintenance. See also and .
