与「FutureWork」相关的搜索结果

Is it Google's responsibility to ensure employees eat well in office cafes? Food director Michiel Bakker says "we're not the food police" but can be "architects" of healthy choices on menus at #WSJFutureFest# #FutureWork#

AI Coding 时代，好的编程习惯仍然重要 最近做一个 Agent benchmark，发现不能简单地用开发者视角来评估一个编程任务对 AI 的复杂度。 比如一个重构任务：把一个几千行的大文件，按功能拆成十多个小模块。 这个任务对开发者来说其实不算难，主要工作就是移动代码、整理 imports、编译验证，新手也能搞定。 所以想着用一个简单的任务来做一下 benchmark，结果却出乎意料。 Claude Code 判断这个任务比较大，尝试拆了一部分，提了个 PR 写了 Future work 打算分步来。 我自己的 Agent 是“硬上”，往完整拆分的方向推进了更多，但代价也很明显：Token 消耗是 Claude 的几十倍，后面大量时间都花在反复读文件、修编译错误、再读文件、再修错误上。 这让我意识到，人觉得简单的任务，对 Agent 不一定简单。 对人来说，这类重构很多时候就是“把这一段挪过去”。但对 Agent 来说，它要先分批读大文件，记住哪些函数和哪些测试有关，再生成一堆跨文件修改，最后通过编译错误一点点补洞。看起来像机械活，实际变成了一个高 Token、高状态管理成本的任务。 前一段时间看到有人说，AI Coding 时代，拆分模块这些编程原则没那么重要了，反正人也不看代码。现在看，我不太同意。模块边界清楚、文件粒度合适、依赖关系简单，不只是方便人读，也是在帮 Agent 降低任务复杂度。 从另一个角度看，现在 Agent 的读文件和改文件工具，对这种重构也不太顺手。 Coding Agent 改文件，主要还是文本替换。比如 Claude Code 常见的是 old_string / new_string 模式：先给出一段旧文本，再替换成新文本。Codex 常用的是 apply_patch：生成一个类似 git diff 的 patch，表达把旧的内容替换成新的。它们都适合小范围修改，但如果要删除一大段旧代码，或者把一批函数挪到别的文件，模型往往还是要先把原始内容读进上下文，再生成一大段替换或 diff。 所以我后来给 Agent 一个提示，让它先用脚本、sed、perl 这类工具把大文件粗拆开，直接把旧内容删掉，写到新文件中，然后再逐个慢慢修，它的完成度确实高了许多。Agent 默认不会这样做，主要是因为系统提示词里会强烈要求 Agent 用内置工具修改文件，而不是命令行工具。 再往前想一步，Coding Agent 可能还需要更高级的编辑工具。不是只给它一个“替换文本”的接口，而是先通过 parser、LSP 或 compiler 建立代码结构，让 Agent 可以像 IDE 一样做重构：移动函数，删除 impl block，整理 imports。不知道是否有朋友做这方面的尝试。 总的来说，即便是 AI Coding 时代，好的编程习惯还是有价值的。尽量在早期通过 harness engineering，把好的编程习惯变成 Agent 的默认工作方式，比后来再重构的成本要小很多。

Automations can now run in the same thread, so Codex can pick up where it left off, with the original context intact. It can schedule future work and wake up automatically to continue long-term tasks, from landing open PRs to following up on tasks or staying on top of fast-moving conversations.

Three days ago I left autoresearch tuning nanochat for ~2 days on depth=12 model. It found ~20 changes that improved the validation loss. I tested these changes yesterday and all of them were additive and transferred to larger (depth=24) models. Stacking up all of these changes, today I measured that the leaderboard's "Time to GPT-2" drops from 2.02 hours to 1.80 hours (~11% improvement), this will be the new leaderboard entry. So yes, these are real improvements and they make an actual difference. I am mildly surprised that my very first naive attempt already worked this well on top of what I thought was already a fairly manually well-tuned project. This is a first for me because I am very used to doing the iterative optimization of neural network training manually. You come up with ideas, you implement them, you check if they work (better validation loss), you come up with new ideas based on that, you read some papers for inspiration, etc etc. This is the bread and butter of what I do daily for 2 decades. Seeing the agent do this entire workflow end-to-end and all by itself as it worked through approx. 700 changes autonomously is wild. It really looked at the sequence of results of experiments and used that to plan the next ones. It's not novel, ground-breaking "research" (yet), but all the adjustments are "real", I didn't find them manually previously, and they stack up and actually improved nanochat. Among the bigger things e.g.: - It noticed an oversight that my parameterless QKnorm didn't have a scaler multiplier attached, so my attention was too diffuse. The agent found multipliers to sharpen it, pointing to future work. - It found that the Value Embeddings really like regularization and I wasn't applying any (oops). - It found that my banded attention was too conservative (i forgot to tune it). - It found that AdamW betas were all messed up. - It tuned the weight decay schedule. - It tuned the network initialization. This is on top of all the tuning I've already done over a good amount of time. The exact commit is here, from this "round 1" of autoresearch. I am going to kick off "round 2", and in parallel I am looking at how multiple agents can collaborate to unlock parallelism. All LLM frontier labs will do this. It's the final boss battle. It's a lot more complex at scale of course - you don't just have a single train. py file to tune. But doing it is "just engineering" and it's going to work. You spin up a swarm of agents, you have them collaborate to tune smaller models, you promote the most promising ideas to increasingly larger scales, and humans (optionally) contribute on the edges. And more generally, *any* metric you care about that is reasonably efficient to evaluate (or that has more efficient proxy metrics such as training a smaller network) can be autoresearched by an agent swarm. It's worth thinking about whether your problem falls into this bucket too.

AI Practical Use #3#: Let AI help you with Excel data analysis. AI 实用玩法第 3 个： 让 AI 帮你做 Excel 数据分析。 Here is a very common office situation: You have an Excel file with sales data, costs, profit, regions, products, and dates. Normally, you may spend 2 hours writing formulas, checking data, making summaries, and building charts. But with AI, you can finish the first draft in about 10 minutes. 一个很常见的办公场景： 你手里有一份 Excel 数据， 里面有销售额、成本、利润、区域、产品、日期。 以前你可能要花 2 小时： 写公式、查数据、做汇总、看趋势、做图表。 现在可以先交给 AI， 10 分钟生成初步分析结果。 You don’t need to manually type every complex formula. Let AI help you: Build formulas Summarize key findings Find abnormal data Compare trends Suggest chart formats Create a report structure 你不需要自己一个个输入复杂函数。 可以让 AI 帮你： 生成公式 总结关键结论 找出异常数据 对比趋势变化 建议图表形式 生成汇报框架 Here is a simple prompt: 这里有一个简单提示词： Please analyze this Excel data. Help me build the right formulas, summarize the key findings, find possible errors or abnormal values, and suggest the best chart or report format. I will review and verify the final results. 中文版本： 请分析这份 Excel 数据。 帮我生成合适的公式，总结关键结论，找出可能的错误或异常值，并建议最适合的图表或汇报格式。 最终结果由我来审核确认。 The key idea is simple: AI does the heavy first draft. You review the logic and final result. 核心思路很简单： AI 负责先把复杂工作做出来， 你负责审核逻辑和最终结果。 Before: 2 hours manually writing formulas. After: 10 minutes with AI assistance. 以前： 手动写公式、做分析，可能要 2 小时。 现在： 借助 AI，10 分钟先完成初稿。 AI is not here to replace your judgment. It helps you save time on repetitive work, so you can focus on checking, thinking, and making better decisions. AI 不是替代你的判断力。 它是帮你节省重复劳动的时间， 让你把精力放在审核、思考和决策上。 Let AI write the formulas. You review the results. 让 AI 写公式， 你负责审核结果。 That is a smarter way to work. 这才是更聪明的办公方式。 #ChatGPT# #AI# #AITools# #Excel# #ExcelTips# #DataAnalysis# #Productivity# #WorkSmarter# #OfficeWork# #BusinessTools# #Automation# #DigitalTools# #TechTips# #FutureOfWork# #PromptEngineering#