与「Cursor」相关的搜索结果

每当有交易所被攻击的时候，FTX就要被拉出来鞭尸一次。 FTX 当年那些投资如果没被破产清算，现在大概值 $2060 亿， 光 Anthropic 一项就 $1705 亿，Cursor 翻了 1.5 万倍。 SBF 挑项目的眼光确实没得说， 可惜这钱现在跟他一毛关系都没有。 挪用用户资产的都改亖啊！🫡

终于有人把这事做了！不用碰 Python，零依赖 JS/TS 直接拿 A股/港股/美股/基金/期货/期权全市场行情 stock-sdk，1.9K stars，内置 92 个 MCP 工具直接喂给 AI。 以前前端想做行情看板，行情工具基本全是 Python 生态，要么自己起后端，要么忍受财经接口 GBK/并发/批量各种坑。 stock-sdk 不一样，v2 架构大改，命名空间 API + 统一符号模型，零依赖，浏览器和 Node 18+ 双端直接跑。 核心能力： 1️⃣ 一套 API 覆盖 A 股、港股、美股、公募基金、期货、期权，实时行情、K 线、分钟线都能直接调 2️⃣ 资金流、龙虎榜、融资融券、大宗交易、涨跌停池、盘口异动、板块资金这些 A 股常用数据也做进去了 3️⃣ 自带 MACD、RSI、KDJ、BOLL、ATR、SAR 等技术指标，还能直接识别指标信号 4️⃣ 内置 Screener + 本地回测，不只是拿数据，筛股和策略验证也能直接做 5️⃣ 筹码分布也已经支持，A 股 / 港股 / 美股都能本地计算获利比例、平均成本和筹码区间 6️⃣ 最关键的是 MCP 已经原生做好了，Claude、Codex、Cursor 可以直接调用这些金融工具，不用你再包一层接口 我觉得它现在最有意思的一点，是已经从“股票数据包”慢慢变成了 Agent 的金融基础设施。 上面 AI 负责研究，下面 stock-sdk 负责行情、指标、选股和回测。 做股票 Agent、AI 投研，或者想给自己的量化系统补一套统一数据层，这个很值得留着。

这个开源项目系统整理了 35 家 AI 公司的 AI 工程师面试题，全部来自 “公开报告的面试经历” 来自 @outcome_school 团队 @pallavishekhar_ 开源发布，内容几乎涵盖了 OpenAI、Anthropic、DeepMind、xAI、DeepSeek、Kimi、GLM 等 AI Labs，Cursor、Cognition、ElevenLabs 等 AI Native 团队和 Nvidia、Microsoft、Amazon、Apple 等头部大厂。 覆盖的岗位头衔也非常多：AI Engineer、LLM Engineer、Gen AI Engineer、ML Engineer、Research Engineer、Applied Scientist、FDE、MLOps/LLMOps 工程师等。 开源地址： # 内容架构：一个精心设计的双层结构 第一层：跨公司通用题（Common Questions）。 作者把在多家公司反复出现的题目只列一次，标注"Asked at"哪些公司，按十大主题组织： 1. LLM 内部机制与架构 — attention 缩放因子、KV cache 内存公式推导、MQA/GQA/MLA、FlashAttention、BPE、RoPE/YaRN、Chinchilla scaling laws、MoE、解码采样策略、lost-in-the-middle、RMSNorm、SwiGLU 2. 推理、服务与 GPU 性能 — prefill vs decode、continuous batching、PagedAttention、投机解码、量化（FP16→FP4）、五种并行策略、TTFT/TPOT 指标、H100 上的 roofline 计算、vLLM/SGLang/TensorRT-LLM 选型、“如何把服务成本降 10 倍” 3. RAG 与检索 — 分块策略、BM25 vs 稠密检索、重排序器、HyDE、权限感知检索、ANN 索引、索引新鲜度、答案归因 4. Agent 与工具调用 — ReAct、MCP、工具 schema 设计、多智能体编排、Agent 记忆、循环终止条件、人类审批 5. 微调与对齐 — RLHF/DPO/GRPO/RLVR 全谱系、LoRA/QLoRA 数学、灾难性遗忘、“提示 vs RAG vs 微调”决策框架、蒸馏、reward hacking 6. 评估与可观测性 — LLM-as-judge 及其偏差、幻觉检测、基准污染、Agent 评估、回归门禁 7. 安全与负责任 AI — 提示注入（直接/间接）、OWASP LLM Top 10、护栏、Constitutional AI、红队 8. 多模态与语音 — VLM、语音 Agent 延迟预算、barge-in 打断处理、级联 vs 端到端语音、ASR/TTS 评估 9. AI 系统设计 — 十类高频设计题（千万级文档企业 RAG、代码助手、客服 Agent、Text-to-SQL、LLM 网关、数亿用户聊天服务等） 10. 编码题 — 从零实现 attention、KV cache、BPE、采样；LRU 缓存、令牌桶限流器、异步批处理器、SSE 流解析器、最小 Agent 循环 第二层：35 家公司的专属章节，分为五大梯队： 1. 前沿实验室（12 家）：Anthropic、OpenAI、Google DeepMind、Meta、xAI、Mistral、Cohere、DeepSeek、月之暗面（Kimi）、智谱（GLM）、阿里（Qwen）、Sarvam AI（印度） 2. 大厂 AI 组织：Microsoft、Amazon、Apple、NVIDIA、Tesla，以及一组消费级 ML 公司（Uber/Netflix/LinkedIn/Airbnb/Pinterest/Spotify） 3. AI 基础设施公司：Databricks、Groq、Together AI、Hugging Face、Scale AI、Perplexity 4. AI 原生产品公司：Cursor、Cognition（Devin）、Sierra、Harvey（法律）、Glean、 AI（机器人）、Waymo 5. 前向部署/企业 AI：Palantir # 题目分布透露的行业信号同样值得关注 1. 公司的差异化考察方向，和它的商业模式严丝合缝。 这是最能体现整理功力的地方： · DeepSeek、月之暗面、智谱、Qwen 的题目深度绑定自家论文——MLA、auxiliary-loss-free 负载均衡、Multi-Token Prediction、MuonClip、DualPipe、长上下文扩展、GLM 的 thinking 模式。面试这些公司等于面试它们的论文，还要求 PyTorch 从零实现 MoE 路由。 · Groq 的题全是 SRAM-only 架构下的 roofline 重推演：“没有 HBM，decode 的 roofline 论证哪里变了”、“确定性在 p99 层面到底买到什么”。 · Apple 清一色端侧：3B 模型在手机上跑、PTQ vs QAT、不采集用户内容的前提下用设备信号改进模型、30+ 语言区无法记录用户内容的评估方案。 · CharacterAI 是推理经济学：“我们的服务成本被 KV cache 而非权重主导，降一个数量级，代价是什么”。 · Harvey（法律）和 Abridge（医疗） 考的是领域约束下的工程：200 页信贷协议里第 140 页的条款依赖第 8 页的定义术语怎么检索、生成的病历中出现了患者没提过的药怎么当作安全事故处理、PHI 如何约束整个架构。 · Palantir 的招牌是 "decomposition" 轮：把“一家货运铁路公司每年因机车非计划停机损失数千万”分解成工程计划。 2. 编码轮的形态正在发生实质性变化。 文档里反复出现的一类题，与传统 LeetCode 明显不同： · “实现一个内存 KV 存储：先 SET/GET/DELETE，再加事务 BEGIN/COMMIT/ROLLBACK，包括嵌套事务”（OpenAI、xAI 都问） · “给你一个 LLM 推理引擎的调度器类，其中一个方法是空壳，没有规格没有文档。说说你头三十分钟干什么”（xAI） “重构这 120 行能跑但很乱的代码，不许破坏测试”（OpenAI） · “对 5 万个文档跑 LLM 调用，API 限 100 并发、偶发 429 和超时，把 Python 写出来”（Anthropic） 考察重心从算法记忆转向增量需求下的代码演进能力、并发正确性、真实工程约束下的取舍。 3. “AI 协作轮”作为新题型已经进入正式面试流程。 这是文档里最前沿的信号： · Anthropic 部分机器学习岗有 AI-collaboration 轮：现场给你 Claude，考察的是你如何指挥它和验证它的产出，而不是你自己写。 · Meta 2026 年的流程新增三阶段 AI 辅助编码轮（探索修复 → 实现新功能 → 扩展改进）。 · Cursor 的 onsite 是两天在真实 Cursor 代码库上做一个功能（或 8 小时远程版），明确考核你对 AI 工具的使用效率和自主 scoping 能力。 · Sierra 给你两小时和任意 AI 工具，看你选择做什么。 xAI 有四小时限时产品构建。 4. FDE 成为一级岗位类别。 Anthropic、OpenAI、Databricks、Scale、Together、Sierra、Harvey、ElevenLabs、Palantir 的章节里都有 "Applied and Forward-Deployed Scenarios" 专属题库——典型题目如“企业客户说 Claude 幻觉太多，你是驻场工程师，头 48 小时做什么”。这对应了 AI 公司向企业交付方式的转变：模型能力差距收窄后，落地能力成为差异化。 5. 硬核系统题的普及。 "H100 上 70B 模型 batch size 1 的 roofline 计算"、"估算 70B 模型的 GPU 显存（权重 + KV cache + 激活 + 碎片）"、"p99 延迟在部署后翻倍但模型没变，走一遍诊断”——这类题横跨 NVIDIA、Together、OpenAI、Perplexity 等多家，说明推理性能的量化直觉已成为 AI 工程师的通用素养，而非基础设施工程师的专属。

“记得她说过的每一句话，也记得你答应过的每一件事。” 哈哈哈哈，就问你怕不怕！ Relate 把聊天里的承诺、待回复消息、关系或项目进展和重要日期存下来，之后可以直接查询、提醒，也能交给 Claude、Cursor 等工具读取。

阿里把团队内部用了两年的官方 AI Code Review Skills 开源了，采用 “确定性工程 pipeline + AI Agent” 的混合架构，专门解决通用 Agent 做代码审查时 “漏审、定位漂移、质量不稳” 的老问题。 40.5K ✨ 开源项目 OpenCodeReview： # 核心设计：确定性工程 pipeline × Agent 各司其职 确定性工程负责硬约束： · 精确文件选择：用代码决定哪些文件必须审、哪些要过滤，不依赖模型自觉； · 智能文件捆绑：把相关文件合成一个审查单元（例如 message_en.properties 和 message_zh.properties 捆绑），每个单元以上下文隔离的 sub-agent 运行，分治策略让超大变更集也稳，且天然支持并发（默认 8 个文件 worker）； · 细粒度规则匹配：内置约 54 个按语言/文件类型的规则文档（Java、Go、TS/JS、Python、Rust、SQL/XML mapper、properties 等），用模板引擎而非自然语言把规则匹配到文件特征上，从源头消除信息噪声； · 外部定位与反思模块：评论的“落点”和“内容”分别由独立的 re-location 和 reflection 模块系统性校正，这正对“位置漂移”痛点。 Agent 负责动态决策： · 深度优化的场景 prompt（内部分为 plan → grouping → main → memory_compression → re_location → review_filter 多个任务模板，可在 internal/config/template/prompts/ 看到）； · 从海量生产环境的 tool-call 轨迹（调用频率分布、单工具重复率、新工具对调用链的影响）反向蒸馏出的专用工具集，包括全文件读取、代码搜索、其他变更文件查阅等，比通用 agent 工具箱更小更稳。 # 能力面与生态集成 功能上覆盖：workspace/分支区间/单 commit 审查、断点恢复（ocr session）、全文件 scan（无 git 历史也能审计陌生代码库）、本地 Session Viewer 网页查看与回放、SARIF/JSON 输出、OpenTelemetry 可观测性、MCP Server 扩展。 作为 “Skills 生态” 级项目，它的形态相当完整：既提供 npm 全局 CLI，也提供可移植的 Agent Skill（skills/open-code-review/SKILL.md，带标准 frontmatter，可直接被兼容 skill 的 agent 加载），还有面向 Claude Code、Codex、Cursor、Kimi Code、OpenCode 等平台的插件，每种都封装成斜杠命令或可调用 skill。LLM 侧兼容 OpenAI、Anthropic、AWS Bedrock 三类协议，并可直接复用 Claude Code 的 ANTHROPIC_* 环境变量。 其中一个设计很巧妙：Delegation 模式（ocr delegate preview/rule）。此时 OCR 只做自己擅长的确定性部分（文件选择和规则解析）审查本身交给宿主 coding agent 的 LLM 执行，用户无需给 OCR 配任何 API key。这实际上是把“harness 能力”与“模型能力”彻底解耦。 # 工程质量：超出平均水准的部分 · 安全有正式的 Assurance Case（ASSURANCE_CASE.md）：完整的威胁模型、四条信任边界、T1–T7 威胁逐条给出缓解措施，并按 Saltzer & Schroeder 设计原则和 OWASP Top 10 做了映射。细节经得起推敲：所有外部进程调用只限 git 且子命令硬编码、--end-of-options 防 flag 注入；Agent 读文件路径经 pathutil.WithinBase() 在符号链接解析前后双重校验；本地 Viewer 有 Host 白名单防 DNS rebinding + 严格 CSP。这类文档在一般开源项目里非常罕见。 · 贡献规范近乎严苛（AGENTS.md）：使用 AI 必须在 issue/PR 中披露工具与模型、必须逐行理解 AI 生成的代码、禁止“AI 生成→反复修复→再修复”的循环、禁止把 commit 署名给 AI。源码强制英文（CI 有 english-check，连全角标点都查）、90% 测试覆盖率门槛、-race 与 govulncheck 每次 push 都跑、SPDX 头与 LF 行尾强制。 # Benchmark：数据情况 官方基准 AACR-Bench（已在 Hugging Face 开放）规模不小：50 个流行开源仓库、200 个真实 PR、10 种语言、80+ 资深工程师交叉验证出 1505 条标注问题。结论是同模型对比 Claude Code：Precision 和 F1 显著更高、token 消耗约为 1/9、速度更快。 需要指出两点：其一，Recall 低于通用 agent，README 自己承认这是“以精度换噪声”的刻意权衡，如果你最怕漏问题而非误报，可能不适合；其二，该基准由阿里自建，虽开放了数据集供社区复核，但独立第三方的复现结论目前还少，可以把它当作“有披露的、方向可信的参考”。

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.

💰 Passed $10M/y in revenue + investment gains this year I've always been aggressively increasing my profit margins to as high as possible, especially the last few years, and especially this year where I've reduced my SaaS dependencies to just a handful of companies by vibecoding my own replacements It's now about 94.5% profit! Spend less -> lower costs -> more profit -> more money saved -> more money to invest -> more % returns on investments And at some point that investment return starts to pass by your business revenue which it has for me for about a year now Most of my investments have been simple ETFs like Vanguard S&P500, but also a few lucky stock and startup bets that worked out: Back in 2022, I couldn't get any available GPUs, so I thought it might be smart to buy Nvidia if there's such a shortage and that was a good bet too Then back in 2023 @dannypostma recommended me to invest in the companies we used for our AI inference for our photo AI apps, so I did that too. First I invested in @replicate and then also @FAL From then I just asked every app/service I used if I could invest, like @cursor_ai in 2025 which then got acquired by @spacex recently! My business revenue has remained very stable at about $200K-$250K/mo, but even with that investment returns have now surpassed that Investments fluctuate a lot so some years it's up some years it might be down a lot (who isn't expecting a big crash at some point?), and most investment gains are unrealized (I never sell!), so keep that with a big grain of salt! I keep my revenue/gains together with my profit margin and my sleep score in my situation monitor dashboard, as those are equally important :D Many people in the last decade told me to spend all my money, either personally or with my business to grow it, we don't know how that would have ended up, maybe my companies would be bigger, but I'm happy I did it in my own lean profitable healthy way and it ended up great I think! 🙏😊