eren

122 posts

eren

eren

@eren7262

Katılım Temmuz 2023
48 Takip Edilen2 Takipçiler
eren
eren@eren7262·
@linasbeliunas Here is my opinion - software is not moat , distribution is moat . Every time anthropic launch new tool , it just trand for one week then no one asking them . Look at Claude design. Anthropic just Lunch tool , can't distribute them .
English
0
0
1
33
Linas Beliūnas
Linas Beliūnas@linasbeliunas·
✅ Claude Code ✅ Claude Cowork ✅ Claude Design ✅ Claude Finance 🔲 Claude Marketing 🔲 Claude Sales 🔲 Claude Finance 🔲 Claude HR 🔲 Claude Operations 🔲 Claude Customer …
Claude@claudeai

New for financial services: ready-to-run Claude agent templates for building pitches, conducting valuation reviews, closing the books at month-end, and more. Install them as plugins in Cowork and Claude Code, or use our cookbooks to run them in production as Managed Agents.

English
48
157
1.4K
132.5K
brett goldstein
brett goldstein@thatguybg·
spent like 20hrs making a massive zip file of skills and agents for content creation linkedin, X, longform, launch videos, etc all a prompt away. I used it to write our next launch script. lmk if you want to try it and ill send it over.
brett goldstein tweet media
English
603
19
407
40.1K
Engineering Randomness
Engineering Randomness@EERandomness·
@BradSmi @Microsoft If I found out a lawyer was using Copilot instead of one of the half dozen smarter models I would probably find a different lawyer.
English
9
6
156
10.5K
Brad Smith
Brad Smith@BradSmi·
Today we’re introducing a new Legal Agent in @Microsoft Word, built to support the precision and rigor legal work demands. Every clause matters. Every redline tells a story. That’s why this agent was built to follow the structured workflows lawyers use while keeping them fully in control. Early in my career, I asked for a computer on my desk because I believed technology could change how lawyers work. It did. Today, I believe this next generation of tools will do the same, grounded in trust and responsible use.
English
241
956
6.8K
3.9M
Tom Huang
Tom Huang@tuturetom·
Open Design 正式支持 Kami 设计系统 💥,来自 @HiTw93 的天才作品 这真是我见过最好看的设计系统之一 🔥 再现纸质的荣光 ⚡️ 让任何想法都能够呈现专业杂志/书籍的排版效果🚀 将原生纸质般的感觉带到了 AI 设计的世界,支持文档、简历、作品集、信函 📚 看一眼都觉得赏心悦目,大家可以欣赏一下👇
中文
23
99
902
90.1K
清凤
清凤@qqqqqf_·
做了个叫 Arkloop的东西,是个 Agent 客户端 开源,本地优先,简单优先 你可以把他想象成 claude desktop but open source, 并且带有自己的 taste 哦对了,另说一点,不是任何 agent sdk 套壳,也没有任何 base 任何 claudecode 行为,我一个人打磨了三个月 和市面上大部分产品不同
我花了很多时间在一个细节上 : 减少认知负担 一个例子 : 我平常只用一个模型聊天,那为什么每条消息前面都要告诉我用了什么模型?这是噪音 再举一个 : 开发者总是喜欢让 agent 的 tool use 完整的展示到前端,但是背后真正的用户体验逻辑是我需要知道 agent 在工作/在往哪个方向偏,所以我们并不需要如此详细的信息 设计哲学:认知负担,信息,价值导向,美学 换个话题 我一个人做 Arkloop 用了三个月,现在他能用了,但是它离完美很远 做产品很重要的一件事是…不要闭门造车,也就是我需要你们的真诚建议 引用来自 Arkloop readme 中的一句话 “我欢迎所有形式的贡献。即使你不是开发者,只是一个普通用户——如果你在使用中感到任何不舒服的地方,哪怕只是一点间距、一个颜色、一个很小很小的细节,或者是一个很大的方向,都可以直接开一个 issue。 我认真对待每一个体验细节,你的反馈会让所有人的体验变得更好。 如果你是开发者,Arkloop 的 Agent 核心、记忆系统、hook 机制都是开放的。你可以接自己的 provider、写自己的插件、甚至改掉你不喜欢的任何设计。”

这是我认为整个项目最精髓的一点,我希望看到你们的反馈,不管是细节还是方向 我在用 dify 的时候,我常常发现,一个特别小的间距问题,竟然在这么大的仓库里没人修 因此,我很重视这点理念 Arkloop 现在并不稳定,还有很多不完善的地方。希望大家多多包容,多提意见 另带一提,Arkloop 可以从 openclaw/hermes 导入配置 Github 仓库:github.com/qqqqqf-q/Arklo… Arkloop 官网兼下载:arkloop.cn 关注我的推特:x.com/intent/follow?… 加入 Arkloop 的 telegram 群组:t.me/Arkloop_io
中文
69
38
379
80.8K
Debajyoti
Debajyoti@Mr_Debajyoti·
@sahill_og most of the developers are using his side project and flexing on the internet for using his side project
English
1
0
1
135
Sahil
Sahil@sahill_og·
One word for this guy.
Sahil tweet media
English
116
2
86
11.9K
eren
eren@eren7262·
@nicdunz I am using Gemini daily bro . What's worng with ppl.
English
0
0
5
597
nic
nic@nicdunz·
this is actually sad lol
nic tweet media
English
102
65
4K
148.4K
eren
eren@eren7262·
@HiTw93 Hey i did some fundamental changes on kimi skill, like changing aspect ratio, adding my own chart skill, 65 + layout type. Did you allow to monetize it ?
English
0
0
0
740
Tw93
Tw93@HiTw93·
AI can write now. Most AI docs still can’t land. Kami exists to fix that. 👩‍🚒Kami v1.3.0 is out. Good content deserves good paper. Kami is a layout design system for the AI era, built to make AI-generated documents clear, readable, and memorable. It uses one constraint language across six formats, simple enough for agents to run reliably, strict enough to keep the output coherent and ready to ship. This release brings a denser resume variant, two new slide layouts, stronger brand profile fields for more consistent voice and style, a shared travel block across deck and portfolio layouts, and tighter writing guides across all template types. It also fixes font drift, overflow issues, border artifacts, and layout regressions that quietly ruin otherwise good work. Less patching after generation. Less CSS babysitting. Less rendering surprise. More range. Better paper for AI-native writing. kami.tw93.fun
Tw93 tweet media
English
10
24
433
29.9K
eren
eren@eren7262·
@vaaselene Ya I use Gemini 3 flash in opencode, ya it's great model . If you perfectly prompt it.
English
0
0
0
11
Selene
Selene@vaaselene·
is anyone using Gemini?
English
887
13
1.1K
148.4K
eren
eren@eren7262·
@HiTw93 Intresting - I ask copilot to , dose kimi use any image api key ? That nigga straight up lying and tell kimi don't use any image api key . Did you add new update to kimi ?
English
0
0
0
151
Tw93
Tw93@HiTw93·
如果你在用 Kami,一定要试试这个彩蛋,在你用 ChatGPT 绘图的时候,把这句话贴在后面,会有惊喜。 最近在写《你不知道的具身智能》,这个非常难的文章陆续写了半个月了,在我Coding有点累的时候当做休闲活动放松,要学习的内容太多了,但非常有趣,需要考虑到怎么清晰、好读、易懂,期待创作过程可以和 Kami 继续碰撞出更多 AI时代内容排版的技巧。 👩‍🚒彩蛋在 github.com/tw93/Kami Travel 。
Tw93 tweet media
中文
11
9
162
22.4K
Jahir Sheikh
Jahir Sheikh@jahirsheikh8·
Why is nobody talking about this? NVIDIA is giving developers free access to ~80 hosted AI models via API. Models include: • MiniMax M2.7 • GLM 5.1 • Kimi 2.5 • DeepSeek 3.2 • GPT-OSS-120B • Sarvam-M …and more. Works with Cursor, Zed, OpenCode, Hermes, OpenClaude, etc. Setup: 1. Get API key → build.nvidia.com/models 2. Use base URL: "integrate.api.nvidia.com/v1" 3. Choose model ID (example: `minimaxai/minimax-m2.7`) 4. Plug into your AI IDE / app If you're experimenting with AI apps, this is basically free inference. Most builders have no idea this exists. Thank me later.
Jahir Sheikh tweet media
English
128
231
2.1K
159.4K
eren retweetledi
dhruv
dhruv@dhruvmakes·
Someone make a @opencode Desktop App ASAP
English
15
1
64
10.1K
Nathan Wilbanks
Nathan Wilbanks@NathanWilbanks_·
I've been running the same AI agent every day since JULY 🚨 - 297 days running 24/7 - 993,115 seconds of compute time automated - 5,020,623,362 tokens generated - 127,743 workflows ran - 605,292 tool executions Comment AGNT below to steal my setup 👇
English
191
27
230
27.1K
eren
eren@eren7262·
@ErDkLive @Amank1412 That's ai generated bro . How handwriting so clean . Special in math
English
0
0
0
2.1K
DK
DK@ErDkLive·
@Amank1412 Ans is - 1
DK tweet media
English
33
31
721
104.4K
Aman
Aman@Amank1412·
Average MIT Questions.
Aman tweet media
Français
235
306
4.3K
2.3M
DeepSeek
DeepSeek@deepseek_ai·
🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/De… 🤗 Open Weights: huggingface.co/collections/de… 1/n
DeepSeek tweet media
English
1.6K
7.7K
45.1K
9.6M
eren
eren@eren7262·
@jasonkneen Not available for windows ? Please add windows support too.
English
0
0
0
352
Jason Kneen
Jason Kneen@jasonkneen·
Introducing "OpenClicky" OpenClicky.io -- the worlds first agent for your cursor with the name "OpenClicky" Built by GPT-5.5 based on the initial open-source (now closed source boo!) "Clicky" app, the aim is to get parity (and more) with this version. More details and repo 🧵
Jason Kneen tweet mediaJason Kneen tweet mediaJason Kneen tweet mediaJason Kneen tweet media
English
32
12
175
16.9K
Michel Lieben
Michel Lieben@MichLieben·
I'm giving away the Claude Code skills we use to manage $300k/mo in ad spend at ColdIQ. 4X ROAS on $1M+ spent. Ivan, our head of growth, built them off 300+ hours running ad campaigns for our clients. They run Google, Meta, and LinkedIn ads from the terminal in plain English: → bulk edits across platforms → custom audiences from CRM lists → creative fatigue detection before CTR dips → bid adjustments at scale → performance audits across periods Reply "ads" and I'll send the full repo. Must be following.
Michel Lieben tweet media
English
5.5K
364
4.1K
432.3K