smallshen
2.2K posts
smallshen
@smallshen2
NYC 18yo student 学生, 173cm & 50kg 🙅 Kotlin/Typescript | Fullstack /不含负能
Katılım Mart 2021
429 Takip Edilen703 Takipçiler
smallshen retweetledi
smallshen retweetledi
smallshen retweetledi
有Garry Tan在那一定是低水平chat🤪
Y Combinator@ycombinator
We’re bringing Jensen Huang to Startup School for a fireside chat with @garrytan! From co-founding @nvidia in 1993 to building the backbone of the AI era, Jensen helped turn GPUs into the engine of modern computing. Apply to attend: events.ycombinator.com/startup-school…
日本語
smallshen retweetledi
最近刷到一个看起来没用但是很喜欢的项目：claude-receipts
github.com/chrishutchinso…
每次和 AI 聊完以后，就可以生成一张消费小票，可以打印出来，贴到墙上，看看当贴满的时候，你的项目到底做的怎么样？
有种怪异的浪漫，如果不想纸质的，用 html 的电子版也行，但是感觉差点事。
中文
devin part of this video is not sped up btw
Cognition@cognition
Earlier this week we announced Devin in your terminal. Now Devin is inside your shell. Hit Ctrl+G and it sees what you see to instantly help you out. try it: `devin shell setup`
English
为什么你应该关注我
@simon_he1995
1. 我所有的仓库都是免费开源的
2. 我不靠推文流量赚钱，原因是曝光一直不达标
3. 我写的 #markstream-vue，比vercel还快
4. 我为人和善，从不主动与人起冲突
Jason Young@Jason_Young1231
为什么你应该关注我@Jason_Young1231 1. 我不靠推文流量赚钱，原因是曝光一直不达标 2. 我和各大厂商都没有合作关系，原因同上 3. 我的推文对你有用的可能性微存 4. 我的头像是小岛秀夫，小岛秀夫谁不爱呢
中文
说一下 Cursor 一个被低估的能力，onboarding env
对于一个桌面项目，配置好了环境之后，cursor 做好了有 computer use 的 linux desktop sandbox，这使得 web 或者支持 Linux Desktop 的 desktop app 可以让它自己调试、验证，然后给你视频证据
con 的 Linux 支持的工作我之前因为本地的 Linux Desktop 在远端，调试过程中需要自己在 loop 里，花费了不少时间也没端到端调通，丢给 cursor cloud agent，一个 shot 就给我调通了
Wey Gu 古思为@wey_gu
非常开心跟大家宣布 con 发布了哈 它是一个 terminal emulator with AI harness, nothing more 它由 rust + libghostty 构建，高性能、GPU 加速是基础 con 专为传统的、至今仍重度用 terminal 的用户准备。 如果你希望用一个顺滑、顺眼的 terminal，但是同时有想拥有一些内置的 agent harness 能力，不再需要更多复杂的东西，con 可能是你的另一个 terminal 哈。 我现在比如做产品的 release 这样的 workflow 已经完全用 con 在做了。 con 可以随时隐藏 agent panel、或者方便的 broadcast 输入框（还有模式自动区分命令与自然语言），原生支持 skills。 欢迎大家来试玩哈，现在是 beta 阶段。
中文
前阵子用了kimi 2.6的preview版本，生成的代码质量真的很差，而且速度也很慢，因此需要多轮修正才能达成和sonnet 4.6相似的水平。可我当时是觉得sonnet 4.6 变笨了才用的kimi 2.6, 用完kimi 2.6觉得笨版sonnet 4.6也比kimi 2.6好
Kimi.ai@Kimi_Moonshot
Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…
中文
English
The hardest thing about agents and backends is durability. @workflowsdk fixes this.
That LLM you're calling *will* go down. That service *will* rate limit you. That database *will* unexpectedly slow down. You *will* get paged 💀
I've been looking for a unicorn for a decade. I wanted the level of reliability of combining stuff like SQS / Kafka / microservices, and I absolutely did not want *that* at the same time 😂
Truly reliable systems like that are notoriously difficult to reason about, to develop locally, to test, to simulate, to deploy… Workflow SDK solves that without compromises.
We're doing what Next.js did for the frontend, but for one of the most important problems of the new generation of backend applications.
Notably, Workflow SDK has an incredible self-hosting and multi-cloud story from day 0. We've taken amazing lessons from Next.js and poured them into the many Worlds (adapters) you can deploy to.
Congrats to Pranay and the Workflow team on a generational ship: vercel.com/blog/a-new-pro…
Vercel@vercel
Vercel Workflows is GA. Your code is the orchestrator. Ship agents, backends, or any long-running process without managing queues, retries, or workers. vercel.com/blog/a-new-pro…
English
smallshen retweetledi
@PromptLLM But it is really usable for me? only I feel this way? It’s super consistent, predictable behavior, especially in coding.
English
@aye_aye_kaplan It would be great if tune composer to not call bash tools that much, it literally tries to call bash tools even for simple task where it is not required at all
English
It’s an excellent model. My personal opinion is it’s near Opus quality (indistinguishable to me for most tasks), but way faster and way cheaper.
Enjoy!
Cursor@cursor_ai
This weekend we're doubling Composer 2 usage in our new interface. Open Agents Window, pick Composer 2, and start building! No hourly limits. x.com/cursor_ai/stat…
English