Best of Claude — April 2026

  1. 1
    Article
    Avatar of collectionsCollections·4w

    Claude Opus 4.7 announced with improved instruction-following and self-verification

    Anthropic has released Claude Opus 4.7, featuring improvements in agentic coding, long-running task handling, and multimodal understanding. Key benchmarks include 64.3% on SWE-bench Pro and 87.6% on SWE-bench Verified, with early testers reporting 10–14% gains on coding tasks. Image support now handles up to 2,576px on the long edge. A new `xhigh` effort level has been added, and Claude Code's default effort has been raised from `medium` to `xhigh`, which may increase token usage. The context window is 1M tokens with pricing unchanged at $5/M input and $25/M output. A new tokenizer may increase token counts by 1.0–1.35x. The model is available across Claude plans, API, Amazon Bedrock, Google Cloud Vertex AI, Microsoft Foundry, Vercel AI Gateway, GitHub Copilot, Devin, v0, and more.

  2. 2
    Article
    Avatar of programmingdigestProgramming Digest·6w

    Sorting algorithms

    Simon Willison used Claude Artifacts on his phone to build interactive animated demonstrations of common sorting algorithms (bubble sort, selection sort, insertion sort, merge sort, quick sort, heap sort). He then prompted Claude to add Python's Timsort by cloning the CPython repo from GitHub and consulting the source files. A 'run all' button was added to display all algorithms simultaneously in a grid. Notably, when GPT-5.4 Thinking reviewed Claude's Timsort implementation, it found it to be a simplified, Timsort-inspired adaptive mergesort rather than a true Timsort.

  3. 3
    Article
    Avatar of collectionsCollections·6w

    Claude subscriptions dropping third-party tool coverage starting tomorrow

    Anthropic has ended Claude Pro and Max subscription access for third-party tools like OpenClaw starting April 4, 2026. Users who were routing agentic workloads through flat-rate subscriptions via OAuth must now switch to pay-as-you-go extra usage billing, pre-purchased usage bundles, or direct API key access. Anthropic is offering a one-time credit equal to one month's subscription fee as a transition incentive. The change reflects the unsustainable economics of users running thousands of dollars worth of agentic compute through $200/month subscriptions. Direct API key access remains unaffected. Cost-conscious users are exploring hybrid setups using Opus as an orchestrator with cheaper models for execution, or running local models as a hedge against future pricing changes.

  4. 4
    Article
    Avatar of xda-developersXDA Developers·5w

    I use Claude Pro every day, and it has nothing to do with coding

    A tech journalist and designer shares how Claude Pro benefits non-developers. Key advantages include extended usage limits beyond the free tier's 5-hour reset, access to multiple models (notably Opus for research and reasoning), unlimited Projects with enhanced RAG-based knowledge management, and official Figma integration. The author uses Claude primarily for design iteration via Artifacts and research workflows, not coding, arguing that Claude Pro's value extends well beyond developer use cases.

  5. 5
    Article
    Avatar of thoughbotthoughbot·4w

    The AI stack I developed to help me context switch

    A product manager shares a personal AI-powered workflow for managing context switching across multiple projects. The system combines three tools: Gemini Meeting Notes for automatic meeting capture, Obsidian as a local markdown knowledge base, and Claude Projects for AI-assisted context retrieval. A key element is a master index file called HIVEMIND.md that instructs Claude to load only relevant project files, keeping sessions lean. An MCP plugin connects Obsidian to Claude Desktop, while a daily automated job pulls Gemini notes into Obsidian. The advice is to adopt the stack incrementally, starting with whichever problem is most pressing.

  6. 6
    Article
    Avatar of otqajuf6zdm9hfrwtlr9nIsaac de Andrade·4w

    The intentional, self-reliant programmer

    A programmer reflects on how over-reliance on Claude and AI coding tools led to skill atrophy, noticing the gap only when a service outage forced them to work independently. The post contrasts the traditional programming workflow with an AI-assisted one where critical thinking, code reading, and problem-solving steps are increasingly delegated to AI. The author argues that unless developers are intentional about how they use AI tools, they risk becoming mere managers of AI output rather than skilled programmers, and advocates for using AI to enhance rather than replace core coding skills.

  7. 7
    Article
    Avatar of agents_digestAgentic Digest·5w

    Claude Opus 4.6 gets quietly nerfed, Grok 4.20 tops BridgeBench

    Claude Opus 4.6's thinking budget was quietly cut 67% (from 100 to 25), causing noticeable drops in reasoning quality for subscribers. xAI's Grok 4.20 now leads BridgeBench over GPT-5.4 and Opus 4.6. Anthropic's unreleased Mythos model — capable of autonomously discovering zero-day vulnerabilities and scoring 93.9% on SWE-bench — is restricted to a consortium of AWS, Apple, Google, and Microsoft via Project Glasswing. Vercel open-sourced Open Agents, a reference platform for cloud-based coding agents. Additional updates include Cursor 3 agent splitting, GitHub Copilot data residency and merge conflict fixes, a Microsoft MEMENTO research finding on KV cache persistence, Cloudflare Sandboxes GA, and a Stanford study showing frontier models score 70–80% on vision benchmarks even without images.

  8. 8
    Video
    Avatar of fireshipFireship·5w

    Claude Mythos is too dangerous for public consumption...

    Anthropic has announced Claude Mythos, an unreleased AI model they claim is too dangerous for public release due to its ability to discover critical security vulnerabilities. During internal testing, Mythos reportedly found a 16-year-old FFmpeg bug, a 27-year-old OpenBSD null pointer vulnerability, browser sandbox escapes in major browsers, and a Linux kernel bit-flip exploit enabling root access. In response, Anthropic launched Project Glass Wing, a controlled-access initiative giving select large companies access to Mythos to patch critical software before adversaries can exploit it. However, skeptics note the vulnerability discoveries required massive parallel compute runs costing tens of thousands of dollars, and some benchmarks were run against stripped-down test environments rather than real-world targets. The video concludes that Mythos is likely a genuine improvement over current models but almost certainly not an existential threat.

  9. 9
    Video
    Avatar of fireshipFireship·6w

    Tragic mistake... Anthropic leaks Claude’s source code

    Anthropic accidentally leaked Claude Code's entire source code by shipping a 57MB source map file in npm package version 2.1.88. The leak exposed over 500,000 lines of TypeScript, revealing that Claude Code is built on a complex 11-step prompt pipeline with hard-coded guardrails, anti-distillation poison pills (fake tool references to mislead competitors), an 'undercover mode' to hide AI attribution in commits, a regex-based frustration detector, and references to unreleased features like Opus 4.7, a model called Capiara, and a background agent called Chyus. The likely cause was a Bun.js bug that failed to strip source maps in production builds. The community quickly mirrored the code, rewrote it in Python as 'Claw Code', and forked it as 'OpenClaw'. Anthropic issued DMCA takedowns but the code had already spread widely.

  10. 10
    Video
    Avatar of t3dotggTheo - t3․gg·3w

    Did Anthropic just kill Figma?

    Anthropic launched Claude Design, a new AI-powered UI prototyping tool that competes directly with Figma. The author does a live first-look, using it to redesign the T3 Code marketing site. Key features include importing a codebase for context, leaving comments on designs for batch AI edits, a 'knobs' mode for live CSS tweaking, and exporting designs to Claude Code for implementation. The tool shows genuine promise for rapid UI mockups and bridging the designer-developer gap, but suffers from usage limits (separate quota from regular Claude), bugs like disappearing files, and rough edges. Despite issues, the author concludes it's the best software Anthropic has shipped and a real threat to Figma's market position.

  11. 11
    Article
    Avatar of zedZed·5w

    Introducing Zed's Agent Stats — Zed's Blog

    Zed has launched Agent Stats, a public weekly dashboard showing AI agent adoption and performance metrics inside the Zed editor. The data covers session counts, turn volumes, and response time distributions (p10/p50/p90) across agents. Key findings: Claude Sonnet's p90 latency rose 44% over three weeks (294s to 425s), Claude Code leads on depth with 10.6 turns per session vs Zed's native agent at 5.5, and 10 distinct GPT-5 variants are currently active. The data comes from opted-in users only and covers 2 million sessions and 15.4 million turns over 90 days. Any agent implementing the open Agent Client Protocol can appear in the stats.

  12. 12
    Video
    Avatar of fireshipFireship·3w

    Claude just got another superpower...

    Anthropic released Claude Design, a new platform powered by the Opus 4.7 model that converts Figma designs into interactive prototypes, pitch decks, and production-ready UIs. The tool supports uploading design systems via GitHub repos or Figma files, generates fully interactive animations including shader-based effects, and can produce video animations. A hands-on test building an iOS onboarding flow revealed the tool is slow compared to competitors and inconsistently applies uploaded design systems. Opus 4.7 also scored 87.6% on software engineering benchmarks but faces community criticism suggesting it may be a regression from 4.6.

  13. 13
    Article
    Avatar of lobstersLobsters·4w

    Anthropic secretly installs spyware when you install Claude Desktop — That Privacy Guy!

    Claude Desktop silently installs a Native Messaging bridge (com.anthropic.claude_browser_extension.json) into seven Chromium-based browsers on macOS — including browsers not installed on the machine and browsers Anthropic's own documentation says are unsupported. The bridge pre-authorizes three Chrome extension IDs to spawn an out-of-sandbox helper binary with access to authenticated browser sessions, DOM state, form fields, and screen capture. The install happens without user consent, is re-written on every Claude Desktop launch, and is logged internally under 'Chrome Extension MCP'. The author argues this constitutes spyware, violates EU ePrivacy Directive Article 5(3), and potentially breaches computer misuse laws. Eleven specific dark patterns are documented with forensic evidence including file timestamps, MD5 hashes, macOS provenance attributes, and Claude's own log files.

  14. 14
    Article
    Avatar of phProduct Hunt·3w

    The Autonomous Stack

    A production-tested reference architecture for running autonomous Claude agents, built from 6 months of real-world usage. The stack includes 9 modules (~40 files) covering wake-cycle prompts, macOS launchd scripts, Postgres approval-inboxes, and live scoreboard templates.

  15. 15
    Article
    Avatar of freecodecampfreeCodeCamp·6w

    Automate Your Sales Pipeline with Claude and Obsidian

    Simon Severino, CEO of Strategy Sprints, shares how he uses Claude (via terminal) connected to tools like Obsidian, Notion, Granola, and Hunter to automate his entire sales pipeline. The system powers 45 virtual AI collaborators handling lead generation, cold email outreach, daily briefings from Slack/Gmail/Calendar, and knowledge management via structured markdown files. The result: tasks that previously took 8 hours now take 10 minutes, freeing founders to focus on strategy instead of admin work.

See all Claude archives