与「Change」相关的搜索结果

Kami v1.12 is a quiet one. No new templates, no new looks, just a version you can trust more. It now plans a document before laying it out, changes only the part you asked to fix and leaves approved pages alone, tells you honestly what it checked and what it skipped, and never lets a failed build overwrite your last working PDF.

DeepSeek-V4-Flash can now run 2× faster locally with DSpark! ⚡️ DSpark enables V4-Flash-0731 GGUFs to generate ~1.4–2× faster with no accuracy change. DeepSeek-V4-Flash-0731 can reach at 120 tokens/s. GGUFs: Guide:

Sam Altman asked Elon Musk what he'd do if he were 22 again. Not "build Tesla." Not "start a rocket company." Two words: be useful That's the whole framework. It sits on two questions almost nobody asks themselves. How much better is your solution than what already exists? How many people can it actually help? Multiply the two. That's your real impact. Every company that has ever changed the planet started by solving a useful problem for a specific group. Nobody who set out to "change the world" ever did. The companies that transformed anything started by making one boring, useful thing 10x better. 22-year-olds looking for a moonshot miss the actual moonshot sitting in the boring problem next to them. Be useful. Ship it to a small group. See if they can't live without it. Repeat. What's the most important problem you think still doesn't have a real solution? Drop it in the replies.

We tried using Meta's new Muse Code agent, but it has a bug that doesn't let it sign in from a docker container. So we did a fun experiment: Meta claims Muse Spark 1.2 was co-trained with their Muse agent harness. So we extracted instructions from their system prompt and added them to the Cline harness. TL;DR of this special prompting: - Trust source code over the user prompt, so read every call site and existing tests before starting the task - Weigh edge and error cases as heavily as the happy path - Always reproduce the bug before fixing - Don't trust the first passing test suite, and verify suspicious looking half-baked tests - Never stop at just editing, keep working until the change is verified complete. We then asked this modified harness to fix a real bug from our repo, and compared the results to the original Cline agent harness. Results: - Used 2.7x fewer tokens (19.7M → 7.2M) - Finished 2x faster (49min → 24min) - Cost 2.4x less ($7.69 → $3.25) Same Muse Spark 1.2 model, same task, only the prompting changed. Incredible how much of a performance gain Meta was able to achieve training it on these special instructions!

1/ Over the past few weeks, we rebuilt CyOps from the inside out. We consolidated 15 branch tips and used a sanitized handoff from another Codex session to preserve decisions, security invariants, test evidence, and remaining risks. Here’s what changed. 🧵

开发系统最极致高效的Agents.md，没有之一： # AGENTS.md ## Core Principles - Choose the simplest implementation that fully satisfies the current requirements. Avoid unnecessary abstraction, configuration, indirection, or speculative extensibility. - Make the smallest necessary change that fixes the root cause. Do not refactor unrelated modules or change strategy semantics unless explicitly requested. - Grow the system in layers. Start from the smallest working end-to-end version and add new capabilities incrementally. Never replace a working system with unfinished complexity. - Reuse existing project components before creating new ones. Prefer extending proven modules over introducing parallel implementations. - Prefer well-maintained libraries when they reduce overall complexity or improve reliability. Do not reimplement common functionality without a clear benefit. - Keep components modular with clearly defined responsibilities. Avoid unnecessary coupling between strategy logic, execution, accounting, replay, and infrastructure. - Design for long-term maintainability once a feature or strategy has been validated. Do not over-engineer speculative ideas before evidence exists. --- ## Strategy Development - Validate hypotheses with historical replay before introducing forward-only logic whenever historical validation is possible. - Every trading strategy must progress through Replay → Shadow → Canary → Live. Do not skip validation stages. - Base design decisions on measurable evidence rather than intuition. Optimize only after demonstrating that an edge exists. - Treat every strategy as an independent contract. Do not silently alter frozen behavior without explicit authorization. --- ## Existing Systems - Do not break running Shadow or Live systems for unrelated work. - Preserve compatibility only when required by active production or validation workflows. Otherwise, remove obsolete code instead of accumulating compatibility layers. - Reuse existing infrastructure whenever possible, including replay engines, accounting, execution, wallet management, order book handling, logging, monitoring, and daemon frameworks. --- ## Engineering Standards - Prefer deterministic behavior over hidden automation. - Fail loudly when assumptions are violated. Do not silently ignore errors or fall back to unexpected behavior. - Keep configuration minimal. Introduce new configuration only when behavior genuinely needs to vary. - Remove dead code instead of leaving unused paths behind. - Write code that is easy to inspect, replay, test, and reason about. - Keep implementation consistent with existing project architecture unless an architectural change is explicitly requested. --- ## Scope Discipline - Implement only the requested scope. - Do not introduce unrelated optimizations, redesigns, migrations, or feature expansions. - Non-blocking findings outside the requested scope may be noted separately but must not be merged into the current task. - Consider a task complete once its agreed acceptance criteria are satisfied. Treat subsequent improvements as separate work items.

Today we are releasing Cloudflare OS, a chatbot with connectors, just like every other tech company is doing. Except actually, it's different. This is a remake of Sandstorm[.]io, my startup from 10 years ago, except this time built on Cloudflare Workers (the platform I've spent the last 9 years building) and deeply leveraging AI. This is more or less the culmination of my secret 10-year master plan. This is a full-on personal app vibe coding platform, in which the sandbox is so secure that you can pretty much go wild -- the AI cannot introduce a significant security bug. We believe a company's security team can feel comfortable giving non-technical users permission to vibe code and then sleep soundly at night. How is that possible? It's the Sandstorm security model, revisited. A "Gadget" is the same thing as a Sandstorm "Grain": a fine-grained app instance. For example, if you have a document editor app, each document runs as a separate instance of the app, in a separate sandbox (one "Gadget"). This means two things, both of which I think are Big Deals: 1. The platform can manage all access control, by controlling who can access the Gadget at all. There is no way the Gadget can accidentally leak itself to an attacker -- even an attacker who has access to other Gadgets based on the same app. 2. Since everyone is running their own copy of the code, everyone can freely *modify* their copy of the code. Think about #2# a bit more. What if, when you wanted a new feature in the software you are using, you could just prompt your agent to add it? This doesn't work in the cloud Software-as-a-Service model, because you are not running your own copy of the app. Sandstorm tried to change that 10 years ago, but the world wasn't ready, because not enough people had the skills or patience to actually modify their software. AI has changed that. Now you just ask the agent -- the same agent that you are using to help you interact with the Gadget can also modify the code of the Gadget. And it is so fun.

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!

The Senate leaves for August recess on Friday. If the Clarity Act gets its floor vote first, more than 70 million American crypto owners gain the core protections investors in every other market take for granted. Here's what changes the day it becomes law. 🧵

Claude + TradingView has changed the way I trade forever. Every trader NEEDS to be using this combo - it's insane. Today, I'm leaking my top prompts. 🧵: 10 insanely powerful Claude x TradingView prompts.👇