Claude

Benjamin Cherny said Anthropic trains Claude against prompt injection and that Claude Code’s model, probe, and auto-mode layers can reach 0% attack success in next week’s defaults. The claim comes from an Anthropic engineer rather than an independent benchmark.

Developers shared workflows that turn idle AI accounts into scheduled assistants for commits, research, repo cleanup, and notes. Shared designs add spend caps, Apple Notes routing, Obsidian output, and coworker controls.

Viral posts claim public Claude chats and artifacts were indexed by search engines. Examples allegedly include API keys, resumes, legal notes, dashboards, project plans, and medical summaries.

Anthropic’s developer update adds per-agent effort settings, seeded session creation, webhooks, sub-agent event streaming, and up to 500 skills per session. The release gives teams finer controls for managed agent runs.

Peter Yang shared Thariq’s explanation that Anthropic cut Claude Code’s system prompt by 80% as newer models need fewer examples and more room to reason. The same discussion covered /loop, /goal, workflows, and long-running agents.

ClaudeDevs said Pro, Max, Team, and seat-based Enterprise users keep 50% higher Claude Code weekly limits through August 19. Users had warned the promo’s end would sharply cut effective usage.

ClaudeDevs says Artifacts now support public links, multiplayer editing in Claude Code, and creation through Claude Tag. A workflow post shows Claude Tag dashboards edited by collaborators or local Claude Code sessions.

Kitze posted screenshots and a join link suggesting Fable access is included with Anthropic Max. ClaudeDevs also said five-hour and weekly limits were reset for all users.

Posts quote Anthropic saying paid Claude plans keep Fable 5 access through July 12, five days past the expected cutoff. Creators used the reprieve for audits, handoffs, and planning.

Official demos show Claude via Higgsfield MCP building small apps such as Ad Studio, NutScan, a handwriting-to-font tool, and a hand-tracked solar system app in one session. The demos frame Higgsfield Apps as a one-prompt path from idea to deployable mini app.

Fable 5’s included Claude access is set to end at 11:59:59 p.m. PT on July 7. Creators shared last-day MCP and prompt workflows for apps, sites, campaigns, triage, and a SNES game port.

Min Choi collected Claude Fable 5 builds spanning a native Command & Conquer iOS port, a Subway Surfers clone, procedural 3D worlds, dungeon generation, and Blender assets. The examples show developers using Fable 5 across mobile ports, browser gameplay, and 3D asset workflows.

Creators spent the first full day using Claude Design for landing pages, brand kits, and slide layouts, with exports into Claude Code. Reports say it works well for wireframes and iteration but can burn quota quickly and still struggles with precise layout and brand cleanup.

Fresh HN discussion and creator posts say Opus 4.7's tokenizer change, xhigh defaults, and adaptive thinking can make sessions costlier or harder to steer. Users also report normal workflows triggering safety refusals or burning large chunks of monthly limits in a single project.

Anthropic launched Claude Design in research preview to turn chats, files, and screenshots into prototypes, slides, and one-pagers. Early users praised design-system matching and code export, but hit high token and rate limits.

Anthropic released Claude Opus 4.7 with adaptive thinking, xhigh effort, and new Claude Code controls including auto mode, recaps, and ultrareview. The update also changes token use, adds a tokenizer update, and fixes rate limits for longer coding and creative sessions.

Designers said AI-assisted coding can get flows working but still needs help on multi-step interactions, so they compared Claude chats, code examples, and manual tweaks. If you are polishing micro-interactions, check the Framer, Rive, and Figma Smart Animate recommendations before picking a build path.

Three builder threads shared reusable layers around model APIs: per-user usage gateways, audits for Gemini-enabled GCP keys, and config-driven routing that swaps providers without app rewrites. Wrapping rate limits, key scope, and model choice in one layer helps teams ship multi-user apps without scattering provider logic.

Community plugins now add multi-agent orchestration and self-hosted repo tours to Claude Code, including five execution modes, 32 agents, and generated code maps. Install them to package repeatable coding and onboarding workflows as skills instead of custom setup.

Glass says its Mac editor can tap existing Claude, ChatGPT and Gemini subscriptions inside one coding workspace, avoiding separate API keys and usage meters. Compare the flat-subscription workflow against Cursor-style billing before you move a product build.

A creator-shared Claude prompt pack lays out a First Principles sequence, Feynman rewrite, assumption audit, and from-scratch rebuild prompts. Use it as a reusable prompt recipe for research and writing, not as an official Claude feature.

A shared prompt pack uses Claude's XML structure for channel planning, title testing, upload systems, Shorts funnels, retention rewrites, and competitor audits. Use the templates when you want the model to ask for constraints before it drafts strategy.

Revise debuted as a document-first editor that keeps rewriting, proofreading, and generation inside the page instead of a separate chat window. Writers should compare the inline workflow against copy-paste prompting, especially when structure and revision history matter.

Posts summarizing Anthropic guidance recommend XML-style tags for task, context, constraints, and output structure, plus nested priorities and examples. Use it when briefs keep drifting, but treat claimed quality gains as anecdotal until you test your own prompts.

One filmmaking loop starts with a ShotDeck frame, uses Claude to reverse engineer lens and lighting choices, then sends ten variations into Nano Banana Pro. Run the loop repeatedly if you want frame study to become practical lookdev instead of passive inspiration.

Google AI Studio is being used in workflows that turn one AI concept image into a working website, sometimes with Claude Sonnet for cleanup. Try it to prototype landing pages before opening Figma or handing work to a developer.

Claude users are sharing 12-step research prompts for mapping papers, finding contradictions, and drafting literature reviews, alongside in-chat interactive charts. Try the workflow to turn source material into briefs and explainers faster.

A creator thread packaged 12 Claude prompts for presentation blueprints, hooks, slide scripts, visual direction, objections, and rehearsal. Use them to structure pitch decks, treatments, and client meetings when delivery matters as much as the slides.