# Development Articoli collegati

Il Centro Notizie HTX fornisce gli articoli più recenti e le analisi più approfondite su "Development", coprendo tendenze di mercato, aggiornamenti sui progetti, sviluppi tecnologici e politiche normative nel settore crypto.

Claude Code's Shocking Origin Exposed: It Evolved from Safety Alignment, Boris: Only 1% Complete

**"Claude Code's Astonishing Origin Revealed: Born from Safety Alignment, with Only 1% Done"** This article traces the epic development of Claude Code, Anthropic's groundbreaking AI coding assistant. Its origins are surprisingly rooted in an internal safety alignment (Alignment) project. The journey began in 2021 with early prototypes like a VS Code extension, but the project was nearly forgotten due to immense infrastructure challenges in creating a true "agentic" coder. Key breakthroughs came from research teams focused on autonomous software engineering, developing core components like bash tools and code search. An internal CLI tool named "clide" emerged but was too超前 (ahead of its time), being clunky and slow. The project's fate changed in September 2024 when Boris Cherny joined. Tasked with "agentic coding," he built a simple CLI prototype. A pivotal moment occurred when he used `clide` to generate a complete pull request from an issue description, revealing the assembled potential of earlier research. A small team then executed a furious two-week sprint to build the core product. Launched in February 2025 as Claude Code, initial feedback was mixed. However, with the release of the Claude 3.5 Sonnet model, its capabilities skyrocketed, fundamentally altering software development workflows in Silicon Valley. Notably, Boris Cherny himself reached a point where 100% of his coding was done silently by Claude Code in the terminal. Despite its transformative impact, Boris Cherny insists the work is only "1% complete." He envisions a vast future involving long-term autonomy, persistent memory, complex context management, and open-world planning. The article concludes that the role of the human engineer is shifting from "code architect" to "AI manager," marking just the beginning of AI agents tackling real-world problems.

marsbitIeri 12:31

Claude Code's Shocking Origin Exposed: It Evolved from Safety Alignment, Boris: Only 1% Complete

marsbitIeri 12:31

Why Did Codex and ChatGPT Merge? What's Next for Codex? OpenAI Core Leader Answers Everything

In 2026, OpenAI's Codex saw explosive growth, with weekly active users surging over 5x to 5 million since January, driven largely by the February launch of its desktop app. Codex desktop lead Andrew Ambrosino explains key shifts behind its evolution. A core change is the inversion of development costs: implementation is now cheap, while curation and taste—judging which of many AI-generated prototypes is valuable—have become the new scarcities. Ambrosino defines taste as a blend of aesthetics, systems thinking, direction, and semantic coherence in interaction. He notes AI still struggles with design because evaluating it requires human cultural context and abstract reasoning about how components relate—capabilities beyond current models. Timing is critical: the same Codex app would have failed months earlier; success hinges on the model's capabilities at launch. Roles are blurring within his team, with engineers, designers, and PMs overlapping significantly. However, Ambrosino cautions against eliminating specialized roles entirely, as each field retains deep expertise. On AI-assisted development, the focus has shifted from measuring code written by AI to distinguishing between supervised and unsupervised generation. A current challenge is teaching models to simplify code, not just add complexity. The merger of Codex and ChatGPT stems from observed user behavior: non-developers adopted Codex for general knowledge work despite its developer-centric interface. This revealed a collapsing boundary between specialized tools and universal assistants. The vision is a "home base" that orchestrates tasks across external professional tools (like Excel or Premiere Pro) via connectors, rather than rebuilding everything internally. An internal example showed Codex helping edit video by interacting with Premiere Pro's files and even writing a plugin for it. The future direction is a unified, extensible platform that serves as a central hub for automating and managing work across any specialized tool the user employs.

marsbit07/05 05:26

Why Did Codex and ChatGPT Merge? What's Next for Codex? OpenAI Core Leader Answers Everything

marsbit07/05 05:26

OpenClaw and Cursor Just Invaded Phones! Agents Are Now in Your Pocket

AI Agents have officially arrived on mobile. In a landmark move, both OpenClaw and Cursor launched native mobile apps on the same day, fundamentally shifting how AI assistants are accessed and controlled. OpenClaw has released full-featured native apps for iOS and Android. Its "local-first" architecture, developed by the OpenClaw Foundation, keeps user data private by running the agent on a user's private Gateway. The mobile app now allows seamless remote control and approval of the agent's actions directly from a smartphone, with access to device capabilities like the camera, GPS, and contacts. Simultaneously, Cursor, the AI-powered coding tool, launched a public beta of its native iOS app. It enables developers to start and manage cloud-based AI coding agents from their phones. These agents can work asynchronously for extended periods—debugging, writing code, and creating pull requests—while developers are away from their computers. The app sends notifications for key decisions, allowing users to review and merge PRs from anywhere. Together, these releases signal a major shift: AI agents are no longer confined to desktop browsers or terminals. They are becoming persistent, autonomous assistants that work independently in the cloud, with humans transitioning from constant operators to mobile supervisors who approve key steps. The era of pocket-sized, on-demand AI is now here.

marsbit06/30 02:30

OpenClaw and Cursor Just Invaded Phones! Agents Are Now in Your Pocket

marsbit06/30 02:30

The Ethereum Foundation Has Split?! An In-depth Look at Ethlabs' "Bright Future"

"Ethereum Foundation Splits? Understanding Ethlabs and Its 'Bright Future'" Former Ethereum Foundation members Ansgar Dietrichs, Barnabé Monnot, Caspar Schwarz-Schilling, Josh Rudolf, and Julian Ma have announced the launch of Ethlabs, an independent non-profit research and development lab. Announced on June 22nd, the initiative comes amidst discussions about the need for new organizational structures within the Ethereum ecosystem, a point highlighted by Bankless founder David Hoffman. Ethlabs' mission is to establish Ethereum as the foundational settlement layer for the global economy. The organization positions itself as a bridge connecting frontline developers, applications, and user needs with the core protocol. It aims to translate real-world demands into protocol improvements, industry standards, and deployable products. The founding team brings significant expertise: Dietrichs and Monnot are highly cited researchers in areas like Proposer-Builder Separation (PBS) and MEV, while Schwarz-Schilling, Rudolf, and Ma contribute backgrounds in economic modeling, consensus research, and applied cryptography. Initial supporters include BitMine, a major corporate ETH treasury; Sharplink, another treasury firm; and Consensys founder Joe Lubin in a personal capacity. Community backers include figures like Uniswap's Hayden Adams and Base's Jesse Pollak. The timing coincides with internal Ethereum Foundation discussions about "spinout" projects. While Ethlabs and the Foundation share research interests like MEV mitigation, Ethlabs frames its role not as a competitor but as part of a shift from a "single-core coordination model" to a "multi-R&D entity collaboration model." It views Ethereum as a public project belonging to all builders, with Ethlabs as one node in a broader governance network. Ultimately, Ethlabs represents an organizational evolution within the maturing Ethereum ecosystem. The key question is whether multiple research bodies can collaborate effectively to advance Ethereum as a competitive global settlement infrastructure.

Odaily星球日报06/23 09:16

The Ethereum Foundation Has Split?! An In-depth Look at Ethlabs' "Bright Future"

Odaily星球日报06/23 09:16

Codex Goal Mode Usage Guide: How to Make AI Continuously Pursue a Specific Objective

"Codex Goal Mode: How to Make AI Work Continuously Toward a Specific Goal" OpenAI's Codex "goal mode" (/goal) transforms the AI from a reactive code assistant into a proactive execution agent capable of working autonomously for hours or even days to achieve a defined objective. To maximize its effectiveness, follow these key principles: 1. **Define Clear, Verifiable Exit Criteria:** The goal prompt should be a concise, measurable success condition, not a lengthy specification. Use quantifiable metrics like "reduce build time by 30%" or "achieve 100% test parity." 2. **Provide Initial Guidance and Tools:** Direct Codex toward likely problem areas and specify available tools (e.g., browsers, testing environments) to prevent it from exploring unproductive paths. 3. **Enable Progress Measurement:** Equip Codex with ways to track advancement, such as creating comparison tools for visual tasks or evaluation sets, ensuring it can gauge its own progress. 4. **Use a Realistic Execution Environment:** For tasks like performance optimization, provide access to environments that closely mimic production (e.g., similar configs, databases) to yield valid results. 5. **Be Cautious with Visual Goals:** Avoid vague "pixel-perfect" instructions. Instead, supplement visual references with functional checklists or design system specifications to prevent Codex from obsessing over minor details. 6. **Implement Progress Tracking:** For long-running tasks, have Codex commit code to draft PRs, update progress documents, or send Slack updates to maintain visibility into its work. 7. **Review and Consolidate Results:** Once the goal is met, instruct Codex to review its work, clean up ineffective experimental code, and reflect on what strategies succeeded or failed. Ultimately, using goal mode shifts the developer's role from writing prompts to managing a persistent engineering agent—defining objectives, establishing metrics, configuring environments, and conducting final reviews.

marsbit06/06 08:11

Codex Goal Mode Usage Guide: How to Make AI Continuously Pursue a Specific Objective

marsbit06/06 08:11

活动图片