与「HOOK」相关的搜索结果

2/12｜Emberkeep：游戏预告片 英文预告，面向 X；前两秒抓住注意力，精修画面，去掉底部进度条。 需要：游戏画面/素材、剪辑和音频。Opus / Sonnet 可负责策划、代码与剪辑编排；缺少镜头时可接 Seedance 等视频模型，音乐音效另备。原 Prompt 没指定视频模型，也没提供完整游戏设定。 完整 Prompt： Create a polished English trailer for an original game, made for sharing on X. Open with a striking hook in the first two seconds, make the visuals more refined, and remove the bottom progress bar. Generated music and sound effects are welcome.

I have to say - for me it started 2 years ago. I remember the moment so well. I was on vacation in Montenegro. Early night. Everyone is asleep and I am on the balcony watching the cruise ships in Kotor bay as the horizon faded to dark. And I think it was Sonet 3.5 (don't quote me). I had just setup a plugin in NeoVim called Avante by @yetone . And it was magic. Coding with AI at the time wasn't the same - I was going function by function. I was accepting diffs one hunk at a time. But I remember that night - from 10 to like 2 in the morning - I built what I thought would have taken me a week (I was rusty and learning the stack). It was an internal tool - a partial JSON parser / repair tool - so you can take half finished JSON and safely turn it into something that would parse. It is more complicated than it sounds. Anyway. I was hooked that day. At the time I was an executive at a Fortune 50, so coding was not in my job description as such. I had hundreds of engineers... but I have to say - it relit my passions, and now as I am (hopefully) building another startup - I still love it. And I still yell at it. And constantly hunt where it is messing up the architecture and adding bloat and.... well you know how it is.

here's a prompt to improve your agent harness based on what we've learned at cursor. enjoy # Improve this agent harness's token efficiency You're working on an LLM agent harness: the system prompt, tool definitions, request assembly, context caching, compaction, and retrieval, and how work is split across agents. Make the agent's runs cheaper without making it worse at its job. - Objective: lower price-weighted token cost per completed task. - Constraint: no measurable drop in task quality. Measure per task, not per request. Every turn resends the prefix (tools, instructions, setup, and the conversation so far), so a change that shrinks each request but adds turns can cost more. Weight tokens by billing type: output, uncached input, and cached input are priced very differently. Work in this order: map the harness and measure the baseline, rank the opportunities, make the changes that are safe to make directly, put the rest behind flags or in proposals, then report. Figures below come from one team's production coding agent and its multi-agent experiments. Use them to gauge magnitude, not as targets. One round of these changes (prompt trimming, tool offloading, cache layout, sparse line numbers, subagent tuning) cut that team's overall token cost about 7% with no loss in quality. The larger percentages apply only to the part of the request each change touched. ## Principles 1. Change what the harness sends, not how hard the model tries. Don't ask the model to conserve tokens. A harness that told its model to "take care to preserve tokens and not be wasteful" found it grew reluctant to take on ambitious tasks and sometimes quit, saying it wasn't supposed to waste tokens. 2. Capable models need definitions, not commands. Lists of "DO NOT", "You must", and "Important", and guards against older models' habits, can usually be replaced with plain descriptions of what each tool does. One team cut about two-thirds of its system prompt this way, and the shorter prompt worked across model families. Instruct only on what the model can't know (the product, the environment, the user's processes) and on quirks you've seen in transcripts. 3. Static context is for what most turns need. Everything else should be discoverable when needed. Less up-front context also means less confusing or contradictory information. 4. Expect removals to win. Guardrails written for weaker models, coordination steps that became bottlenecks, and prompting for behavior the model now does on its own all cost tokens. 5. Real usage decides. Evals are a fast proxy, but they skew toward hard problems and miss the real mix of requests. ## 1. Map the harness and measure the baseline Find: - Where requests are assembled, the system prompt, and tool schemas. If a framework or SDK builds requests, find its hooks for message order, cache control, and tool loading. - How tool results are formatted, and how history is kept, trimmed, or summarized. - How subagents or parallel agents are spawned, if any. - Which models and provider APIs are used. From the provider's docs, get the prompt caching behavior (automatic or explicit breakpoints, TTL, minimum cacheable length) and the prices for output, uncached input, and cached input. - Existing logging, token accounting, and evals. If the harness doesn't record per-request token usage by billing type and cache hits, add that first. Everything later depends on it. Then render a few real requests (from logs, or by running representative tasks) and count tokens per section with the model's tokenizer or the API's usage fields. Produce: - Cost share by source × billing type. Sources: system prompt, tool definitions, skill/rule/integration descriptions, user messages, file reads, search results, command and other tool output, history, summaries, subagents. - Static tokens per request, cache hit rate, and turns per task. - Per tool: the share of runs that call it at least once, and its error rate. Read the rendered requests, not just the templates. Duplication, leaked volatile values, and misordered blocks only show up there. Rank opportunities by share of spend × fraction removable ÷ quality risk. ## 2. System prompt and injected context Label every instruction: - Keep: product or environment knowledge the model can't infer, fixes for quirks seen in this model's transcripts, and rules a mode depends on. - Rewrite: commands and emphasis into plain descriptions. Reminders into constraints: "No TODOs, no partial implementations" works better than "remember to finish implementations." Vague quantities into ranges: "generate 20–100 tasks" gets far more ambitious behavior than "generate many tasks." - Delete: things capable models do by default, guards against behavior you haven't seen from this model, text that repeats tool descriptions, and lines that could contradict a user request. Models trained to rank system instructions above user messages will side with the system prompt. - Move: anything per-user or per-request (date, environment, repo state, lists of skills or subagents, user rules) into a user-role setup message after the cache boundary. Audit other injected context the same way. As models improved, the team behind these figures dropped directory trees, pre-retrieved snippets, compressed copies of attached files, lint errors injected after every edit, forced expansion of short file reads, and caps on tool calls per turn. They kept small, high-value facts: OS, repo status, and open or recently viewed files. Skip checklists for open-ended work. The model optimizes the listed items and deprioritizes everything else. ## 3. Tool definitions Tool schemas ride along on every request. Most tools beyond the core set were each needed in under 20% of conversations, and moving them out of static context cut tool-description tokens 60%. Doing the same for integration tools (such as MCP servers), with names in context and full schemas in one folder per server that the agent can search with grep or jq, cut total tokens 46.9% in sessions that used them. - Keep in static context: high-frequency tools (for a coding agent: read, search, edit, shell), tools the model tries to call even when they're absent, and tools a mode depends on. - Offload the rest: leave a name or one-line pointer and make the full schema discoverable on demand. Group related tools so they load together, and put status (such as "needs re-authentication") where the agent will see it. - Tighten what remains: describe behavior and arguments, and drop usage lectures. - Pick the split by testing a few configurations and tracking tokens, cost, latency, tool-call errors, and task success. ## 4. Cache layout Order each request so the reusable prefix is as long as possible: `tool definitions → system instructions → [breakpoint] → setup message (skills, subagents, rules, environment) → [breakpoint] → conversation` - Keep the prefix byte-identical across turns. Use deterministic tool order and serialization, put timestamps and IDs after the boundary, and don't rewrite earlier messages except when compacting. - Use explicit breakpoints if the provider supports them. Otherwise rely on automatic prefix caching with the stable part first. Respect TTL and minimum-length rules. - Switching models mid-conversation throws away the cache (caches are per model and provider) and hands the new model a history it didn't write. When a different model is needed, run it as a subagent with fresh context. Explicit breakpoints plus moving per-request setup after them cut cold cache misses 20%. ## 5. Tool results and other context added during a run - Large outputs (commands, integrations, logs): write them to a file and return the path, size, and a short tail. The agent can tail, grep, or read ranges for more. Truncating loses data, and inlining bloats every later request. Treat long-running terminal sessions the same way. - High-volume formats: look for overhead repeated on every line or item. Numbering every 10th line of a file read instead of every line cut cache-read tokens 1.6% without hurting citation accuracy. Each number costs 3–5 tokens, and agents read tens of thousands of lines per session. Also check repeated absolute paths, verbose JSON keys, ANSI codes, progress bars, and repeated headers. - Good retrieval saves exploration turns. Adding semantic search alongside grep raised codebase question-answering accuracy 12.5% on average and cut the iterations users needed. - Tool errors waste tokens and leave confusing debris in context. Classify expected errors (invalid arguments, unexpected environment, provider error, timeout, user abort), treat unknown errors as harness bugs, and track rates per tool and per model. One focused effort along these lines cut unexpected tool errors 10×. ## 6. Long runs: compaction, subagents, and model mix - Compaction: keep the summarization prompt short and the summary compact, carry forward plan state and remaining tasks, and save the full history to a file the agent can search for details the summary dropped. A model trained to self-summarize from a one-line prompt wrote ~1k-token summaries with half the compaction error of a multi-thousand-token prompt that produced 5k+ token summaries. Untrained models may need more guidance, so test how short you can go. A more expensive summarization model made a negligible difference. - Scratchpads and running notes: rewrite them instead of appending. For repeated work in one environment, a small agent-maintained notes file with a line budget, loaded at start, is a promising way to shorten later runs. - Subagents: fresh context keeps the parent lean, but isolation adds coordination cost (duplicate or stale work). If the model already delegates on its own, remove prompting that pushes it to. Have subagents return short handoffs: what was done, findings, concerns, and deviations. A subagent should use a different model only when the user or harness says so. - Model mix: in large multi-agent runs, workers used at least 69% of tokens, and over 90% in most runs. A frontier planner with cheap workers matched a frontier model doing everything at about one-eighth the cost. Planner choice still changes worker spend. One planner that cost less on its own saw its workers use several times more tokens, and the run cost more overall. Measure the whole tree. - Routing and reasoning effort: send simple turns to a cheaper model or lower effort, and upgrade only when a stronger model is clearly better. A router built this way matched or beat single frontier models on user satisfaction at 41–68% lower cost. - Reasoning continuity: if the API returns reasoning items (including encrypted ones), pass them back on later turns and alert when they go missing. Dropping them cost one reasoning model 30% on a coding benchmark, and it burned tokens reconstructing its plan. ## 7. Fit the harness to each model Adapt to what each model was trained on instead of forcing one shape on all of them. If you've tuned the harness for a similar model, start from that version. - Edit format: use the one the model was trained on (for example, patch-style or search-and-replace). An unfamiliar format costs extra reasoning tokens and causes more mistakes. - Shell or tools: shell-first models fall back to `cat` or inline scripts. Name tools after their shell equivalents (such as `rg`), and if needed add: "If a tool exists for an action, prefer to use the tool instead of shell commands (e.g. read_file over `cat`)." - Literalness: some model families follow instructions literally and others tolerate imprecision. Some spiral on emphasized wording. Strip caps and emphasis for literal models. - Triggers: some models ignore a tool until told when to use it. A literal trigger works: "After substantive edits, use the to check recently edited files for linter errors. If you've introduced any, fix them if you can easily figure out how." - Progress updates: if a model reports progress through reasoning summaries, keep them to 1–2 sentences that note new findings or a change of tactic, and remove instructions about messaging mid-turn. - Quirks worth a targeted line: hedging or refusing as context fills ("context anxiety"), declaring completion early, stopping to ask permission, and calling tools that don't exist. Tie each added instruction to the transcript behavior it fixes. Re-audit when models change, since guidance one version needed can be dead weight for the next. ## 8. Validate - Offline: run a fixed set of realistic tasks before and after, ideally drawn from real usage and phrased the way users actually write (short and ambiguous). Compare task success, tokens, cost per task, turns, and tool errors. Don't ship a change that lowers success. - Online, if you have users: A/B test each change or small bundle. The primary metric is cost per completed task. Guardrails are task success signals, tool-call errors, latency, turns per task, and cache hit rate. For a coding agent, a good success signal is how much agent-written code survives over time. In general, check whether the user's next message moves on or reports a problem. - Ship only when cost drops and no guardrail regresses beyond noise. Record null results. ## What to change directly and what to propose - Change directly, each in its own revertible commit: token and cache telemetry, deterministic serialization and tool order, moving volatile content out of the cached prefix, explicit cache breakpoints, writing large outputs to files instead of truncating, passing back reasoning items that are being dropped, and fixes for recurring tool errors. - Change behind a flag so it can be tested: system prompt edits, tool offloading, output format changes, compaction changes, and subagent prompting. - Propose only: changes to which models run, routing, reasoning-effort defaults, or how work is split across agents. ## Traps - Asking the model to use fewer tokens or do less. - Truncating tool output. - Dropping reasoning items to save input tokens. - Volatile content in the cached prefix, or tool order that changes between requests. - Offloading a tool the model needs on the first turn or tries to call when it's missing. - Emphasis-heavy prompts (MUST, NEVER, IMPORTANT, all caps), especially with literal models. - Forcing a terser output format than the model was trained on. Fewer output tokens can mean less thinking and worse results. - Optimizing raw token counts instead of cost, per request instead of per task, or evals instead of real usage. - Switching models mid-conversation to save money. - Adding coordination layers that become bottlenecks. ## Report back with 1. The harness map and baseline: cost by source × billing type, with the biggest sources called out. 2. A ranked list of changes: layer, what changes, estimated savings and how you estimated them, quality risk, how to validate, and how to roll back. 3. The changes you made, including a system prompt diff with a keep, rewrite, delete, or move reason for each line. 4. A test plan for the flagged changes. 5. Gaps: anything you couldn't find or measure.

StablePair Hook is now live on Uniswap When a stable pair drifts off its rate, there's value in correcting it Static fees hand that value to arbitrage bots, StablePair's fee scales with the drift and hands it to LPs instead Volatility that used to cost LPs now pays them

AI Engineering Skills Map 系列之「使用 Coding Agent」 吴恩达老师的 AI 工程技能图谱第三篇详细展开： 1. 构建与部署 AI 应用 2. 软件工程基础 3. 使用 Coding Agent（本文主题） 4. 塑造构建方向 吴恩达老师认为：使用 Coding Agent 正在成为 AI 工程师的关键能力，而且它的演进速度比其他顶层技能都快，因为 Agent 本身在 harness 和模型两个层面同时快速迭代。因此，这项技能没有终态，只能靠持续的实验、构建和学习来维持。 # 用 Coding Agent 构建软件的通用工作流 通过访谈数十位顶尖 AI 工程师并复盘自己团队的实践，他归纳出一个一致的高层工作流，分三步： 1. 规划（Planning） 包含两部分：一是头脑风暴，可能涉及研究、实验、理解已有代码库；二是写 spec（规格说明），涵盖需求、技术设计、架构，随后生成执行计划。规划完成后还应审视计划本身：质疑关键假设，检查安全性、过度设计等问题。 2. 执行（Execution） 构建、测试、验证，关键在于把握智能体自主性与人工监督之间的平衡。一是让智能体以"校准过的自主程度"去构建；二是通过自动化和/或人工检查来验证输出。 3. 部署与监控（Deployment and monitoring） 部署可能经由 CI/CD 流水线或额外的人工关卡把关；随后用智能体观察日志、发现问题、提出并执行改进。 这个工作流有两个特别注意： 1. 它与前智能体时代的软件开发流程本质相似。真正变化的是注意力的重心：从写代码转移到决定做什么、设计架构、写 spec、验证输出。 2. 各步骤的时长弹性极大，可以省略。greenfield（从零开始）原型的 spec 可能只是一条快速写下的提示词；而有大量用户的 brownfield（存量）项目的 spec 则需要投入大量精力去撰写和验证。整个流程高度迭代，熟练的开发者知道何时该从后面的步骤退回前面：验证失败就引导智能体重建修复；监控发现问题就让智能体更新系统并重新部署。 # 五项关键技能 1. 指挥工作流（Directing the workflow） 知道如何走完上述每一步，并决定每一步投入多少人力、多少智能体算力，以及何时回退迭代。这背后是对速度、成本、技术风险、人力投入四者权衡的深刻理解，具体体现在：前期研究和规划做到什么程度、哪些关键工作保留人类所有权、如何选择架构、规划产物（如 spec）写多细、如何把工作拆解成可验证的步骤。 2. 赋予智能体自主性（Enabling agent autonomy） 这一节内容最密集，可拆成四个决策点： · 自主程度：盯着它交互式往返，还是委托一大块工作？何时设定明确目标让它循环直到成功？ · 上下文管理：构建过程会经历不同阶段，要判断何时把关键经验、用户反馈、假设（包括中途变化的假设）记录下来供智能体下游使用。 · 并行化：何时把任务拆解后让多个智能体并行，由人或更高层的智能体来编排；以及如何在多个并发会话之间分配人的注意力。 · 安全运行：设置权限、对高风险动作设关卡，在保持开发速度的同时限制泄露、数据丢失等损害。 3. 审查工作成果（Reviewing the work） 出发点是一个基本事实：智能体的输出是不确定的。我们事先不知道它会想出什么好主意，也不知道它会埋下什么 bug。因此审查和验证是拿到想要结果、并在偏离时纠正的关键环节。 具体手段包括： · 设计与任务匹配的测试和验证，按需结合行为验证和功能验证。 · 测试用户流程，可让智能体提供截图作为成功或失败的证据。 · 对定性/行为性评估，可使用评估集（eval sets），可能配合 LLM-as-a-judge。 · 决定测试的自动化程度。某些工作流会把测试完全自动化，让智能体能自行检查、自知何时完成。但必须评估这些测试是否真正对应你的目标，不对应就要演进它们。 · 使用智能体代码审查，运行 AI 驱动的安全和架构审计。 · AI 审查不够时，审慎地插入人工审查——主要审查代码行为，较少审查代码本身——同时探索进一步自动化的可能。 · 验证部署，并用智能体把监控和事故管理运营起来。 这里有一个值得注意的判断：人工审查的对象主要是"代码行为"而非"代码"，这反映了注意力重心的转移。 4. 定制智能体及其环境（Customizing the agent and its environment） 目标是让智能体高效获取所需上下文、访问工具、正确高效地构建。具体包括： · 集成 skills、插件、MCP 服务器，并在不再必要时（如新模型让旧 skill 过时）剪除它们。 · 用 hooks 自动化开发流程中可重复的部分，如触发自动代码审查或 CI/CD。 · 维护常驻上下文（AGENTS.md、CLAUDE.md），记录代码库信息、关键架构假设、代码风格、数据访问模式。 · 跨会话、跨并行智能体保存状态，随时间积累智能体的经验，比如通过运行后复盘记录哪些做法有效、哪些无效。 · 建立一致的约定和结构，让代码库对智能体可导航；定期清理智能体产生的技术债。 · 团队协作时，考虑如何在不同开发者的智能体之间协调上下文。 5. 编码智能体基础原理（Coding agent foundations） 要做好上述所有决策，需要理解智能体的工作机制：如何做代码库搜索/检索、如何管理上下文窗口、不同操作（增加工具调用、MCP 服务器等）如何影响上下文、智能体与子智能体如何交互、智能体是如何通过在 LLM 外包裹 harness 构建出来的。 这种理解让智能体不再是黑箱，帮助你识别典型失败模式： · 把简单方案过度设计 · 因缺乏显式验证流程而丧失严谨性 · 未达目标就停下 · 可能破坏文件或生产数据的动作 同时也帮助你推断智能体的状态、给出正确的指令或上下文来引导它，并在监控运行时更早发现它偏离轨道、需要介入。 # 对行业叙事的批评 结尾处吴恩达老师有一段针对性很强的观点。他认为社交媒体对如何使用编码智能体的描述往往过度简化。让智能体自主运行数小时、消耗数百万甚至数千万 token 有时确实有用，但目前超长时程任务的实际效用——尤其是相对成本而言——被夸大到超出现实。 他的结论是：最有效的编码智能体使用是一个复杂、高度迭代的过程，能够以高水平判断力适时介入，效果远好于放手长跑。

BREAKING: SpaceXAI has released a major new update for Grok Build (v1.0.14) Grok v1.0.14 is a reliability and workflow update for the Grok CLI. It makes OIDC token refresh proactive, lets PostToolUse hooks send feedback back to the model after tools run, adds per-turn token and cost tracking via grok usage, and cuts Windows downloads by about 70%, with a large set of fixes that tighten sandboxing, subagent handling, hooks, and startup. Features: • OIDC token refresh is now proactive by default for better reliability. • PostToolUse hooks can now provide feedback and context to the model after tool execution. • SDK-registered PostToolUse hooks now provide model-facing feedback. • grok usage now shows persisted per-turn token and cost data. • Retry status in composer and title now shows a short reason for the retry. • Models can now declare a different identifier for each reasoning-effort level instead of always sending the same id. • Prompt suggestions now respect remote configuration and default to the current session model. • Windows CLI downloads are now ~70% smaller using the same compressed sidecars as macOS and Linux. Bug Fixes: • grok inspect now correctly shows Claude bypass locks as advisory rather than enforced. • Subagent sessions no longer leak threads or file descriptors when the parent is busy. • Cold startup no longer performs duplicate remote settings fetches. • Compaction failures due to context size now degrade input instead of retrying identically. • --sandbox strict now restricts writes to ~/.grok/sessions only. • Subagent spawning now waits longer on a busy coordinator and shows clearer retry guidance instead of "unreachable". • Failed task and todo tool calls now appear in the transcript instead of disappearing without a trace. • Composer status row no longer collapses or flashes when using double-Enter to send now. • Session close is no longer delayed by a single slow hook; each SessionEnd hook now has its own timeout. • Hook removal in the extensions modal no longer offers actions that the handler will refuse. • Interjections during a turn are now delivered atomically or not at all. • Subagent tasks no longer get incorrectly cancelled when the parent session is waiting for completion. • Workflow detail view now closes the overlay on X or outside click instead of returning to the run list. • Resuming subagents now succeeds for larger transcripts that still fit the model context with headroom. Performance: • Startup now fetches remote settings only once per boot instead of potentially twice. • First message on large repositories no longer waits on repository status scan. • Large session memory no longer blocks the agent during turn completion or subagent spawning. • Signed-in CLI starts faster by serving remote settings from a local cache on warm boots. Download Grok Build: Update to the latest Alpha release: grok update --alpha Update to the latest Stable release: grok update

BREAKING: SpaceXAI has released a new and improved update for Grok Build. v1.0.12 — 2026-08-27 Performance: • Worktree creation is faster by skipping stale reflog copies. Bug Fixes: • Copying wrapped table cells no longer inserts unwanted spaces at line breaks. • MCP server connections that fail transiently now retry instead of staying unavailable. • Waiting on subagents after an interjection no longer blocks on unrelated background work. • Prompt blocks now show friendly hook descriptions instead of internal IDs. • Truncation error message no longer suggests asking for a shorter answer. • Context estimates for conversations with reasoning are now more accurate. • Token usage after rewinding or switching modes now matches the actual server-reported count instead of overestimating. • Context bar now updates immediately when auto-compaction begins instead of waiting until it finishes. • File system monitoring for .NET projects no longer creates excessive watchers on Linux. • Auto recap no longer appears while a background task or monitor wake turn is streaming. Download Grok Build: Update to the latest Alpha release: grok update --alpha Update to the latest Stable release: grok update

发现有不少人吐槽，在RH链上也总能买到冲进去就会归零的币，我不用问就知道都在群里看到CA直接就冲的那种，大凡认真看一下网站，了解下项目机制，看一下当前的市值就不可能买到这样的PVP币。 我一直在强调，RH链是一条有券商TradFi气质的新链，它的使命是把传统股票代币化资产搬到链上，只有存在类似机制的项目才值得观察下冲一冲，我分享几个，我观察到的，几个有点意思的项目： 1） $HOOD10：买卖抽税，用税费去买当前链上流动性最大的10个币，再按轮次空投给持仓达标的人。类似于RH链的“QQQ”大盘指数，只要RH链大盘有热度，这个币本身有交易量，钱包里就能源源不断的收到热门币种； 2） $AI : 是发射台long设计的可以和传统股票组交易对的发射机制，AI代币会交易会燃烧，另一侧的NVDA股票则会慢慢囤入金库，金库壮大可能回去回购或者分发其他股票之类的； 3） $index :买卖代币燃烧税会响应地购买纳斯达克代币化股票，十几分钟一轮分发给持币人； 4） $Hookr: 是把Uniswap V4的Hooks玩法机制应用到RH链发射台的一种尝试，每个新盘都可以挂上Hooks机制的玩法，比如 防狙击，自动燃烧、LP分成、第N刀奖池等等。作为一个技术敏感的博主，真希望这样的发射台有一天成为主角。 那会还看到一个新发射的小盘，机制是用买卖燃烧税，到金库里，然后投票去lighter里做永续合约，要么壮大池子，要么亏光。不过，市值太低了，我就不提了。 还有很多在股票代币化资产基础上融入做做agent管理金库，隐私跨链服务等等很多做实验型项目。感兴趣的话可以都去研究下，绝对不是猫啊，狐狸啊之类的无意义的MEME。 你看，如果你冲着这类品相和审美的项目去买的，即便短期热度没那么高，买进去归零的概率也很低吧。至少晚上可以睡得着觉，等个几天没准就有意外惊喜，我认识的不少朋友都是这样的反馈。所以冲土狗归零的朋友们，到底是什么问题呢？如果永远是P一下就跑，看见CA就冲的姿态，去Solana、BSC找盘子不更成熟一点，为啥非要来RH链。 朋友们，转变PVP思维，拿出投研精神，去找有意思的项目下注，陪伴成长，这才是RH链冲浪在新周期的意义。 Note：以上提到的ticker仅供参考，不做投资建议。因为，类似TradFi和DeFi结合机制的项目很多，市值太高等新的就是了，RH的链上繁荣还很早期，不要怕错过机会。

🤖 AI信号 (RBH) ⚪ 观望 📌 HOOK ($HOOK) CA: 0xa8211c77ddd23e6b0929442d3d3a5bcb7212271f ⏰ 信号时间: 10:25:06 (22秒前) | 币龄: 1小时内 💰 MC: $135,204 | 流动性: $59,927 👥 Holders: 463 | 1h涨幅: +1731% | 1h成交: $139,957 🧠 聪明钱包: 3个买入 (SW-81b8, SW-915a, SW-b776) 🤖 AI 分析（推文12条） ① 叙事：无公开叙事，疑似跟风盘。 ② 推特热度：推文多为同名撞车，CA分散多条链，无法确认针对本币；AI信号提及“各CA混杂，疑”。暂无有效讨论。 ③ 风险评语：dev信息缺失、描述为空；推文出现多CA且有人称“scams and rugs”，某CA前十持仓98%，红旗明显。 ⚠️ 非买入信号·可实现中位−23% DYOR Telegram频道: @ memmememjk