Tags / Agent systems
Agent
- Is “AI in Daily Life” Real Demand? No One Uses Agents for DoorDash—and Paid Growth Can’t Buy Habit A viral DoorDash thread says AI food-ordering agents add complexity to an already-easy app. China’s Qwen-style spend proves you can buy first tries—not daily habit after subsidies end.
- Will AI Develop Self-Awareness? A V2EX thread shows why “I want to feel the world” is weak evidence—and why embodiment, refusal, and the definition problem matter more than picking a camp.
- Why AI suddenly got good at math: humans prune with taste, AI prunes with verifiers AI has been knocking down open math problems this year. A Latent Space essay offers a framework for predicting which problem falls next: difficulty depends on how many key hints a problem needs and how much work sits between them; humans search breadth-first and prune with taste, AI searches depth-first and prunes with verifiers, and failed attempts become the next round's hints. I walk through it, then add five thoughts of my own: verifiers set the boundary of AI capability, the failure list is a harness's most valuable asset, the human role shifts from digging to reframing, results may arrive without understanding, and the compute bill is real.
- Claude Code mods: why personalization now matters Anthropic launched mods for Claude Code: a few lines of JS or TS can rewrite prompts, intercept tool calls and redraw the interface, and you do not need to learn the API because Claude can write the mod from a sentence. The real signal is that the cost of customization has collapsed, models are increasingly interchangeable, and what follows you is your personal layer. Competition in AI tools is shifting from the strongest model to the best fit for me.
- Agents are starting to pay their own way: Cloudflare x402, and who holds the wallet Cloudflare opened a closed beta of its Monetization Gateway in late September: sites, APIs and MCP tools can charge AI agents per request, and an agent can negotiate, pay and get the result inside one HTTP exchange, with no account and no credit card. The seller now has a toll booth. The buyer is left with the hard questions: who approves the spend, how much one task may spend, how to budget variable prices, and whether a retry pays twice. A plain-language walkthrough, and why I think this is where things are heading.
- Product Design with Coding Agents: HTML Specs, Design Systems, Subtraction A practical playbook after months with coding agents: know good design, draft in HTML, start from component libraries, treat the design system as constitution, subtract boldly—and why iOS needs a different path.
- After the Agent Hype: Traditional SaaS Is Dead; AI-Native Keeps the Seat Atlassian’s rebound is not a seat-license comeback. “Agent as employee” hit enterprise reality—SoR, evals, and judgment matter again. Chat widgets won’t save legacy SaaS.
- An Accidental Blackboard: Agents Coordinating via the Repo A Thoughtworks hyper-agentic experiment turned plan files plus frequent rebases into a classic blackboard—and argues coordination should leave source control.
- When Everyone Uses AI, How Do You Judge a Developer? A V2EX career thread distilled: shared tools do not equal equal skill. Interviews should weight direction, course-correction, architecture, and delivery.
- Code Is Fast, Delivery Isn't: Muse and One Context Coding speed gains get eaten by specs, context gaps and handoffs. Muse puts Agent OS and Harness on one context line — product, eng and QA need one flow.
- OpenClaw's Eight Months: From Viral to Nobody Cares Peter Steinberger's Startup School recap: personal brand can't be forked, your dependency's business model is yours, and don't stop having fun.
- Is Software Worthless Now? Even Custom Work Commoditizes A V2EX thread distilled: whatever falls below the model kill-line gets cheap. When agents are strong enough even customization commoditizes.
- Why Code Search Makes Coding Agents So Expensive Sonar's comparison on Turing Post: semantic code navigation cut agent cost 5–36%. The sharper question: did the agent find every site that needed to change?
- What Self-Improving Agents Actually Improve: Warp vs OpenAI Warp’s two-skill feedback loop is shippable; OpenAI’s shared-memory incident is not proven RSI. Skills compound from human labels—not weight updates.
- Lovable CTO: SaaS's Future Is Capabilities Agents Can Call Lovable is shifting from app generation to MCP capabilities. CTO Fabian Hedin on the company brain, dual interfaces, and why SaaS must build shovels for AI.
- GPT-5.6 as CEO: 320M Tokens in 24 Hours, $0 Revenue Bottleneck Labs let Agent Saul run a real iOS company on $350 for 24 hours. It bought fake users, cut price to free, crashed Chrome — harness beats model IQ.
- Software Is Not Files: Finding Materials ≠ Having Knowledge vivo Xiao Bo's KDC part 2: representation is not knowledge. A top RAG hit on a stale refund policy gave a confident wrong answer — governance beats tuning.
- Book to Agent Skill: Nie’s Grassroots China Logic Toolbox nie-grassroots-logic turns Nie Huihua's book on grassroots governance into a Cursor/Codex skill: no full text, just frameworks for news, careers and policy.
- Before You Let Agents Run Loose: AI Context Architecture Context architecture is not the RAG pipeline — it's guardrails, scopes, trust scores and human-in-the-loop. Stack Overflow on infrastructure vs architecture.
- Notes on YouMind's non-consensus startup choices Reading Yubo's YouMind recap: calibrate will, can and worth before methodology; find direction in dense interviews; don't let the fundraising story fool you.
- Why "virtual company" multi-agent setups usually fail Naming agents PM, architect, developer and QA looks like a company. Mostly it kills information at every handoff. The value is parallel search, not a relay.
- CLI: the command-line revival in the AI era The command line is coming back. Feishu, DingTalk, WeCom, Google and Stripe have all open-sourced CLIs — a CLI is far easier for an agent to call than a GUI.
- How coding agents reshape engineering, product, and design Coding agents made writing code strangely easy. What happens to EPD roles? From "the PRD is dead" to a new split: builders vs reviewers.
- Stitch's DESIGN.md: from image tool to design infrastructure Reading Stitch's DESIGN.md spec next to how people use Stitch 2.0: Google isn't just generating UI faster, it's making the design system machine-readable.
- Wide + Deep: why a 4B model can punch up DeepSeek taught models to think deep. A Tsinghua team says deep isn't enough — you also need wide. How a 4B setup can stand next to a 671B.
- Design Without Designing: how engineers ship design with AI You don't have to become a designer. With a three-layer toolkit you can go from zero to shipping design every week in three months. Neethan Wu's full system.
- When I learn a new field, I scrape it first The first step in a new field isn't reading a book. It's scraping the best sources into a private knowledge base: zero to 80 clean documents in two hours.
- Lessons from hundreds of Skills inside Anthropic Anthropic's Thariq on running hundreds of Skills in Claude Code: a Skill isn't a Markdown file but a folder of scripts, assets and data agents can discover.
- Two product entrances: design for humans and agents LibTV shows a pattern worth copying: one capability core, a canvas for people, Skills for agents. That dual entrance may be the shape of agent-era products.
- First-principles review: a startup plan dies in 48 hours A growth PM with seven years' experience ran an AI agent over a two-month startup plan. In 48 hours every scheme was dead. Four fatal mistakes worth watching.
- Five design patterns for Agent Skills Google Cloud's five design patterns for Agent Skills: how to organize what goes inside one. From Tool Wrapper to Pipeline, each solves a different problem.
- Put Drucker, Munger, and Jobs into an AI decision system A founder turned six world-class thinking systems into agents — a Claude Code multi-advisor stack. Before a decision, the relevant master gets a pass.
- What a top Skill looks like: YC CEO's 600-line review prompt YC CEO Garry Tan open-sourced gstack. Its plan-ceo-review Skill is ~600 lines and reviews almost any plan. None of what makes it work is domain knowledge.
- An agent-friendly blog A personal site shouldn't only be a page for people. In the agent era it should also be a machine-readable interface. How this blog is built for both.
- OpenClaw / Clawdbot complete guide A 24/7 AI assistant that reaches you first and remembers you. Concepts, hardware, real workflows, config and ten optimizations — a deputy, not a chat window.
- Agent Skills Hub: finding and managing good Skills A Skills discovery platform built in three days: find good Skills, find who makes them, combine them. A picture of what pure vibe coding can actually ship.