与「ASD、」相关的搜索结果

最近给我每天都在使用的工程师合集技能 Waza 加上了一个很有用的操作以及回复规则，来源于 ASD-STE00，一套最开始用于航空维修文档的简化技术英文标准。 最开始是看到 Andrej Karpathy 的推荐，让大模型参考这一套规范来解释事情，回复会更加易读，刚好晚上有空，我顺着看了看规范和官方的 AI 白皮书，发现它对于词语、条件、和操作顺序的要求，真的非常适合拿来检查 AI 到底有没有把话讲明白讲清楚，想着基于我的理解给大伙更好懂的解释一下。 可以理解飞机维修手册其实面向阅读的人来源于各个国家，英文不一定是对方的母语，比如说修飞机的时候，拆哪一个零件、什么时候可以操作、前一步做到什么地步才可以继续做下一个步骤，是不是感觉非常像现在我们让 Agent 去做一些事情，我们也是想着尽可能 Agent 非常准确快速的做好，并把我们的诉求理解到位。刚好就和这个飞机维修手册上的说话操作规范非常像。 很多时候，一个词语换一个意思，一句话里面漏掉一个条件，面对说明书操作的人可能会做成不同的操作。好比大公司里面，CEO 的想法是经过多轮传递，很容易会导致很多信息失真，最后做出来的东西可能会当时想的完全不一样。 这套标准从我的理解正是用来解决这种说话和执行偏差的问题，它由协作规则和词典组成，词典会限制一个词可以用什么词性、表达什么含义，包括这个行业里面的哪些技术属于可以允许使用。同一个东西也不会为了避免重复就换一个名字去做，操作的步骤会需要写清楚条件和顺序等等这样的要求，其实这些放到技术文档里面也非常好理解。 我在 Waza 里面为了让 AI 更好理解，比如说在 write 写作技能里面我放了这样的例子，让 AI 写出来的内容更加清晰明白。 比如“上传完成后，删除本地文件”，如何被 AI 简化成“开始上传，然后删除本地文件”，会很容易出问题，可能文件还没有传完就被删除掉了，这里的“完成”就是决定了什么时候能删除，是必须存在的词。 再比如“只有检查通过，才允许重启” 和 “检查通过后就重启”，前一句就符合这个要求，后一句没有执行要求的动作容易多出很多可能，“才允许”在这里就是那个保持原意的关键词。 这正是我希望 AI 在日常回复和帮我干活时候要注意的地方，把做的结果讲明白、讲清楚，让它和我都不困惑不懵逼，说到点上，不要我再去多问一句更多的才好。比如说代码改好了、测试通过了、已经推送了、用户可以下载了都是对于结果的详细表述，假如它只回一句“已经修复并验证”，这种情况下，我肯定会继续问，到底解决了啥都好了没。 不过我认为，这里没有必要让 AI 去完整参考所有的标准，归纳起来的规则其实非常短，「同一个对象保持同一个名称，指代不清时写明对象，把条件和例外放在对应动作附近，保留先后关系，分清建议、要求和可能性。已经清楚的话就不改，不要为了简短删掉原因和边界。」 当然你也可以直接安装 Waza 的 clarity 规则来使用，或者直接去这里看看。

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

mattpocock/skills v1.2 is out! We're now the 19th most-starred repo of all time. 13.5m downloads on skills​.sh. Thanks for your support! Here's what's new: - Docs: the community's biggest ask. Every skill documented, with explanations of the main flows + troubleshooting - Claude Plugin: install via Claude's official marketplace - Codex Support: full Codex support via agents/openai.yaml files Updated Skills: - /grilling now asks you questions in rounds, not one-by-one - /prototype now uses HTML instead of a TUI for building logic prototypes - easier to share and far richer - /writing-for-agents renamed from /writing-great-skills, use it for ANYTHING your agents read (AGENTS.md, system prompts, docs) New Skills: - /wizard: tired of provisioning infra? Get your agent to build you a TUI to walk you through it - /to-questionnaire: hit a grilling question you can't answer? Turn the session into a doc you can walk through on a call with a colleague - /wait-what: no idea what the model said? Refocus it in your domain language and simplify with ASD-STE100 Full changelog + docs below. Video soon!

Microsoft's Advanced Shader Delivery technology has now arrived on AMD RDNA 3 GPUs. In testing with a Radeon RX 7600, Forza Horizon 6 now loads in just 4 seconds instead of the previous 90 seconds. The feature precompiles shaders during game downloads and installation, bypassing the need for in-game shader compilation. This cuts load times by up to 95% and virtually eliminates shader stutter for much smoother gameplay in supported titles. Co-developed with AMD, ASD is enabled through the latest Adrenalin 26.5.2 drivers for RDNA 3, RDNA 3.5, and RDNA 4 GPUs. It requires Windows 11 24H2 and updated Xbox services.

这段时间，对我启发最大的一个概念就是“数字孪生（映射）”。我这个人反应有点慢，很多事情我没有彻底开窍以前，我是没什么反应的。可能也是一种ASD。 一旦数字映射，万物皆可算。这不强大吗？

原头像的这条裙子被嘲笑为像50+大妈…今天又穿了，有人过来跟我说这条裙子很好看😂 因为这条裙子我其实买了很多条。 可能是因为ASD的刻板行为，我从小分别因为喜欢反反复复的听一首歌，演奏一首曲子，读一本书，朗诵一首诗，穿同一件衣服（一模一样买了很多件）….而被嘲笑过。比如把同一首曲子演奏100次..队友实在受不了了🤦还有同一道菜做一个月…. 所以至此以后我决定同一条裙子，我一定要买不同颜色的，至此也喜欢上一个同款式会做不同颜色衣服的品牌。

All love and respect between Steve Nash, Grant Hill, and Mike D’Antoni as D’Antoni has been enshrined into the @Hoophall 🙌 Watch the Class of 2026 Enshrinement Ceremony on NBA TV and the NBA App.