# Automation Related Articles

Is Writing Prompts Outdated? AI Programming is Shifting to Loop Engineering

"The era of manually writing prompts for AI coding agents is shifting towards 'Loop Engineering,' where developers design automated, self-managing workflows instead of step-by-step guidance. A loop consists of five core components: Automations (scheduled task discovery and triage), Worktrees (isolated environments to prevent file conflicts), Skills (project-specific knowledge and conventions), Plugins/Connectors (integration with tools like GitHub, Linear, or Slack), and Sub-agents (separate agents for execution and verification). An external memory layer, such as Markdown files or Linear boards, tracks progress across sessions. Tools like Claude Code and Codex now embed these components, enabling loops to run autonomously—discovering tasks, assigning work, checking results, and deciding next steps. This approach amplifies developer leverage but doesn’t replace human judgment. Key risks include 'comprehension debt' (losing understanding of the codebase) and 'cognitive surrender' (over-relying on automation). Effective loop design requires balancing automation with ongoing verification and deep system understanding, making it a more complex but higher-leverage skill than prompt engineering."

marsbit06/10 17:55

How to Conduct Deep Research Using Claude's Dynamic Workflows

The article "How to Use Claude's Dynamic Workflows for Deep Research" discusses overcoming the pitfalls of technical research, where both humans and AI can get overwhelmed by information, leading to vague conclusions. It introduces Claude Code's new "Dynamic Workflows" feature, which automatically designs and executes task-specific workflows before starting a task, unlike simpler "planning modes." This approach incorporates validation, result convergence, and adversarial verification from the outset. The core of Dynamic Workflows is six predefined scheduling patterns that address how to decompose tasks and synthesize results: 1. **Classify-and-Act (Routing):** An agent classifies the task and routes it to the most suitable specialist agent for execution. It's precise and efficient but struggles with ambiguous tasks. 2. **Fan-out & Merge:** The task is split into parallel, independent subtasks whose results are later merged. It's fast and isolates contexts but is more expensive and challenging to synthesize. 3. **Adversarial Verification:** Multiple "challenger" agents critique a worker agent's conclusion, requiring majority approval. This counters confirmation bias and self-assessment errors but relies on verifiable facts. 4. **Generate & Filter:** Multiple agents generate many candidate solutions, which are then filtered against a rubric to output only the best. It fosters diversity but depends heavily on the filter's quality. 5. **Tournament:** Multiple agents compete on the same task, with pairwise comparisons eliminating contestants over rounds to select the best. This offers stable relative judgment but is complex. 6. **Loop:** An agent iteratively attempts a task, learning from errors and adjusting until a stop condition is met. It handles tasks with unknown scope but risks infinite loops without proper design. The author compares their own custom deep-research system, which involved multi-agent analysis and deduplication but lacked goal-oriented convergence, to Claude's built-in workflow. The official workflow adds critical layers: initial problem decomposition, credibility assessment of sources, cross-agent voting to delete weak conclusions (not just averaging), and output tightly focused on the user's original goals and actionable recommendations. This structurally addresses common AI issues like goal drift, premature stopping, context pollution, and output bias. In summary, Dynamic Workflows represent a shift from smarter single conversations to a structured research process, compressing what used to require many dialogues into 3-4 interactions, albeit at higher token cost. The author notes remaining challenges for their specific domain (blockchain research): the need for fact-based verification over official documentation, depth in truly novel interdisciplinary thinking, the practical validation of proposed solutions, and tailoring information density to the audience.

marsbit06/09 03:07

Recursive Self-Improvement AI Gains Traction, Google Pours Cold Water, While DeepSeek and Others Approach the Fringes

The term "recursive self-improvement" (RSI), where AI improves itself autonomously, is gaining momentum in the AI industry. Startups like Recursive Superintelligence and projects such as Andrej Karpathy's Auto-Research aim to create systems where AI designs, implements, and validates its own research, moving toward superintelligence. While Google CEO Sundar Pichai cautions that such exponential acceleration is not yet a reality, progress is evident. For instance, Anthropic reported its Claude Code writes nearly 100% of the team's code, though it still lacks true self-direction. Analysts frame RSI development in stages: "adequacy" (systems functioning without humans), "parity" (matching human research quality), and "supremacy" (exceeding human-AI collaboration). Reaching parity could trigger rapid, unpredictable advancement due to AI's continuous operation. In China, companies like DeepSeek and Baidu incorporate self-optimization techniques without explicitly branding them as RSI, focusing on algorithmic efficiency and reinforcement learning. However, challenges remain, including "model collapse" from training on AI-generated data and the immense computational and open-collaboration requirements. Ultimately, RSI represents a trend of increasing automation in AI development, potentially reducing human oversight in the creation process itself.

marsbit06/06 23:25

Exclusive from Yingke | Tang Wenbin's 'Yuanli Lingji' Merges with Logistics Robotics Company, and Secures Investment from Zhipu, SenseTime, Jieyue, and Others

Exclusive report: Embodied AI company "Yuanli Lingji" recently completed a new round of financing from major AI model firms including Zhipu AI, Stepfun, and SenseTime, alongside continued investments from industrial backers like Huaqin and SAIC Hengxu. Founded in March 2025 by Tang Wenbin, former co-founder and CTO of Megvii, Yuanli Lingji is a general-purpose embodied AI model company. In a notable move, the company has merged with logistics robotics firm "Atomix" (formerly known as Yuanli Juhe) through a share acquisition. Atomix, which originated from Megvii's logistics robotics business led by Tang in 2016 and was spun off in July 2024, has grown to become the world's second-largest supplier of pallet shuttle robots, with annual revenue nearing 1 billion RMB and over 500 projects globally for clients like Uniqlo and CATL. This merger aims to break the industry's "data deadlock" by combining Atomix's extensive real-world operational data from more than 20 countries with Yuanli Lingji's model training capabilities. The company's embodied AI model "DM0" utilizes a cross-domain training approach, integrating internet semantics, autonomous driving rules, and robotics data to achieve hardware-agnostic, precise manipulation even with a compact 2.4B parameter size. The collective investment from key AI players and the strategic merger signal a shift in the competitive landscape, as major model companies pivot from language tokens to physical actions ("from Token to Action"). The industry is entering a consolidation phase where hardware, AI models, data, and application scenarios converge to scale embodied intelligence, a trend mirrored by recent moves from giants like ByteDance and Skild AI.

marsbit06/05 01:07

The Merger of Codex and ChatGPT Marks the Beginning of a Major Reshuffle in Programming Tools

OpenAI is shifting its strategic focus from ChatGPT to Codex, merging them along with the browser tool Atlas into a unified desktop super-app. This move signals an internal belief that Codex, originally a programming tool, represents the next evolution of AI more than conversational models like ChatGPT. Over the past year, Codex's weekly active users have surged past 5 million. The key distinction is that while ChatGPT answers questions, Codex executes tasks. Enterprises increasingly value this ability to get work done over simply receiving advice. Consequently, Codex is attracting professionals beyond developers, including analysts, bankers, marketers, and product managers. OpenAI's reorganization and increased investment in Codex stem from recognizing that the future of AI competition lies in execution capabilities, not just conversation. The company is launching role-specific plugins (e.g., for data analysis, sales, design) to transform Codex into a broad knowledge work platform that automates and redefines white-collar workflows. Beyond being a tool, Codex reflects OpenAI's ambition to redefine software. New features like "Sites"—which generates interactive websites from documents—and collaborative "Annotations" aim to create a paradigm where the AI understands the goal and handles the tools and steps, functioning more like a digital colleague than traditional software. The ultimate goal is a unified experience where the user cares only about the completed task.

marsbit06/04 11:32

GitHub, Transfixed by AI

On the night of February 9th, GitHub suffered a major outage caused by a simple configuration change—reducing a cache refresh interval from 12 to 2 hours—that triggered a cascade of failures. This was not an isolated event, but part of a broader pattern. In early 2026, GitHub experienced at least 8 major incidents, failing to meet its promised 99.9% availability. These outages stemmed from structural issues: explosive growth in load, tight service coupling, and insufficient protection against abnormal traffic. This unprecedented load is driven by AI Agents. In 2025, GitHub handled ~1 billion commits. By 2026, weekly commits reached 275 million, projecting to ~14 billion for the year—a 14x increase. AI tools like Claude Code now contribute 4.5% of all public repository commits, with weekly submissions surging 25x in just three months. AI-generated pull requests jumped from 4 million to 17 million per month in half a year. Unlike human developers, AI Agents work continuously, generating commits at a scale that overwhelms infrastructure designed for human rhythms. The surge also shattered GitHub's business model. Copilot's flat-rate pricing, based on assisting human developers, became unsustainable as Agentic AI sessions consumed resources worth hundreds of dollars for a few dollars in fees. In response, GitHub imposed usage limits and, by June 1st, shifted to a pay-per-use "AI Credits" system. Facing this new reality, GitHub realized a 10x scaling plan was insufficient. It announced a need to *redesign* its architecture for 30x current scale—decoupling services, adding fault isolation, and improving change management to prevent cascading failures. Other platforms like Stripe and AWS are facing similar challenges with AI Agents. Fundamentally, GitHub is transitioning from a human collaboration platform to an "exhaust pipe" for automated AI workflows. Its detailed post-mortem reports aim to maintain trust during this turbulent rebuild. The February outage was not just a technical glitch, but a signal of the software industry's entry into a new, AI-driven era.

marsbit06/04 10:40

Claude Code Introduces Dynamic Workflows: Enabling AI to Form Teams and Collaborate

Claude Code introduces dynamic workflows, enabling AI to coordinate teams of specialized agents for complex tasks. This transforms Claude from a code assistant into a programmable workbench. Workflows address key limitations of single-agent systems: agentic laziness (premature task completion), self-preferential bias (favoring own outputs), and goal drift (losing sight of original objectives). The system allows Claude to dynamically create execution frameworks using JavaScript. It can split tasks, dispatch parallel agents for isolated work (e.g., in separate worktrees), implement adversarial validation, run tournaments, and synthesize results. This multi-agent approach is valuable for tasks requiring deep research, factual verification, code migration, root cause analysis, large-scale triage, and qualitative sorting. Key patterns include: classify-and-route, fan-out-and-synthesize, adversarial verification, generate-and-filter, tournaments, and loop-until-done. While token usage is higher, workflows excel where tasks resemble programming—needing problem decomposition, isolated context, hypothesis testing, and handling many details. They extend Claude Code's utility beyond technical work to areas like business plan review, resume screening, and naming brainstorm. The feature is not a universal solution but points to a future where AI tool competitiveness depends on organizing reliable, reusable, and auditable execution flows for complex goals.

marsbit06/04 02:15

From IDE to Terminal: A Practical Guide to Agent Engineering

marsbit06/03 07:01

跨链桥主动求变，LI.FI用意图架构成为TradFi机构流动性中枢

marsbit06/03 06:35

After 540,000 Lines of Code, Garry Tan Realizes the Old Game of AI Programming Is Over

YC President Garry Tan's project "Garry's List" involved over 540,000 lines of Rails code, but he concluded this approach is outdated. He argues the software industry is stuck in a "Foxconn factory" mindset: building excessive tests, validators, and control logic to constrain LLMs, which have become cheap and capable enough to work autonomously. The old paradigm treated LLM calls as expensive and code as cheap, leading to complex systems to "manage" the AI. This has now reversed. The future lies in "just-in-time software"—using natural language instructions (Markdown-based "skill packs") and minimal code, letting the AI handle the work. Tan advocates for "skillifying" workflows: after an agent completes a task, it packages the process into a reusable, tested skill pack. This shifts value from writing code to designing capabilities. For example, his agent reviewed 85 hackathon submissions in 30 minutes, a task that previously took days. He emphasizes "tokenmaxxing"—willingly spending on LLM tokens to gain a years-long competitive advantage, as costs are plummeting. The core shift is from measuring output in lines of code to focusing on clarity, taste, and judgment. The best future engineers won't write the most code, but will know what to build and how to unlock the most intelligence with the least code.

marsbit06/02 21:38