Sea Frog

101 posts

Sea Frog

Sea Frog

@dave7922

Researcher on deep learning and biomedical imaging.

Katılım Mart 2020
876 Takip Edilen23 Takipçiler
Sea Frog retweetledi
Sam Altman
Sam Altman@sama·
Our new AI-first web browser, ChatGPT Atlas, is here for macOS. Please send feedback! Availability on other platforms to follow.
English
3.3K
1.6K
22.7K
2.9M
Sea Frog retweetledi
OpenAI
OpenAI@OpenAI·
Meet our new browser—ChatGPT Atlas. Available today on macOS: chatgpt.com/atlas
English
2.3K
4.2K
29.8K
14M
Sea Frog
Sea Frog@dave7922·
@dotey 在不能改变模型权重的情况下,如何构建中间层,通过中间层提升最后给用户的答案,比如现在的context engineering,是一个重要方向,尤其是基于大模型的初创公司,这是形成差异化技术壁垒的途径之一。
中文
1
0
0
88
宝玉
宝玉@dotey·
真要做一个自动化写作的 Agent,工作流可能更合适,毕竟步骤相对固定,成本也会更低,Claude Code 可以在中间做工具用,另外 Claude Code 写作能力不一定很好,需要搭配不同的模型组合使用效果更佳。 AI 写出来的内容质量,主要取决于 2 点: 1. 你提供的上下文质量 2. 模型能力 最后才是提示词水平 这篇文章好是因为这个访谈质量好,提供了优质上下文内容,否则很难写出来好的结果。 就好比你现在让模型去翻译,大部分时候如果原文不错,翻译结果也会不错,如果原文不行,翻译不出来好的内容。 这种拿现有资料去重写的,也是类似一种语言的翻译,是大模型所擅长的。
花叔@AlchainHust

Claude Code是最好的自动化写作agent。 这篇3000多字的文章100%是让Claude Code帮我完成的,在小红书数据不错,也引起了很多讨论,但似乎没有任何一个人怀疑这是AI写的文章。 迟点在评论区分享我的写作agent构建方式

中文
16
39
197
98.2K
Sea Frog
Sea Frog@dave7922·
🚨 Google !Gemma 3n 登陆 Play Store! 🔥 纯本地 AI,断网运行,数据 100% 本地! 🎙️ 语音+图片识别! 💻 代码全开源! 个人 AI 助手时代! #Gemma #Google
中文
0
0
0
105
Sea Frog retweetledi
Haider.
Haider.@haider1·
Geoffrey Hinton says I'm more optimistic now, not because we'll control AI, but because we might not need to "don't try to dominate superintelligence; design it to care, like a mother wired to protect her child" Control through attachment, not power. we want AI to be like that
English
228
233
1.5K
347.6K
Sea Frog
Sea Frog@dave7922·
Robotic Biologist: We’re excited to announce BioMARS (Biological Multi-Agent Robotic System), the first system to deeply integrate LLMs & VLMs into a robotic platform for fully autonomous biological experiments. Paper: arxiv.org/pdf/2507.01485 Demo: github.com/AlexandreQ27/B…
English
0
0
2
86
Sea Frog
Sea Frog@dave7922·
Robotic Biologist: We’re excited to announce BioMARS (Biological Multi-Agent Robotic System), the first system to deeply integrate LLMs & VLMs into a robotic platform for fully autonomous biological experiments. paper: arxiv.org/pdf/2507.01485 Demo: github.com/AlexandreQ27/B…
English
1
4
4
846
Sea Frog
Sea Frog@dave7922·
Today we’re launching BioMARS — an autonomous AI lab scientist. BioMARS is the first robotic system that deeply integrates LLMs and VLMs to autonomously conduct biological experiments — from reading literature to executing protocols and detecting errors. Watch the demo video.
English
1
0
1
75
Sea Frog
Sea Frog@dave7922·
@cline should make it work with local model more smoothly. Tried to use it with ollama or llm studio. both have glitches, particular the annoying "API Streaming Failed" problem,
English
0
0
0
107
Cline
Cline@cline·
Just pushed Cline v3.17.12 This release includes free Grok 3 access for 2 weeks, collapsible MCP panels, better file context, and more reliable diff edits. Full details below. 🧵
English
13
16
204
13.3K
Sea Frog retweetledi
Jingyun Yang
Jingyun Yang@yjy0625·
Introducing Mobi-π: Mobilizing Your Robot Learning Policy. Our method: ✈️ enables flexible mobile skill chaining 🪶 without requiring additional policy training data 🏠 while scaling to unseen scenes 🧵↓
English
7
80
318
58.7K
Sea Frog retweetledi
Y Combinator
Y Combinator@ycombinator·
Auctor is building the AI-native platform to streamline enterprise software implementations—capturing requirements, generating artifacts, and keeping everything in sync. Faster timelines, fewer change orders, and teams that stay aligned from day one. ycombinator.com/launches/NT1-a…
English
20
24
189
70.8K
Sea Frog
Sea Frog@dave7922·
还记得你何时加入 X 吗?我知道!
Sea Frog tweet media
中文
0
0
0
27
Sea Frog
Sea Frog@dave7922·
@randyloop 能不能写一个教程?这个很有帮助!谢谢
中文
0
0
0
706
Randy Lu
Randy Lu@randyloop·
研究开源项目前,让 cursor 帮我生成项目 codebase 的 flow chart, 帮助我理解项目
Randy Lu tweet mediaRandy Lu tweet media
中文
17
41
318
49.5K
Leandro von Werra
Leandro von Werra@lvwerra·
Introducing: ⚡️OlympicCoder⚡️ Beats Claude 3.7 and is close to o1-mini/R1 on olympiad level coding with just 7B parameters! Let that sink in! Read more about its training dataset, the new IOI benchmark, and more in Open-R1 progress report #3.
Leandro von Werra tweet media
English
56
212
1.5K
159.3K
Sea Frog retweetledi
Qwen
Qwen@Alibaba_Qwen·
... QwQ-Max-Preview Qwen Chat: chat.qwen.ai Blog: qwenlm.github.io/blog/qwq-max-p… 🤔 Today we release "Thinking (QwQ)" in Qwen Chat, backed by our QwQ-Max-Preview, which is a reasoning model based on Qwen2.5-Max. This model is still for preview. It is highly capable of math understanding, coding, agent, etc. Compared with Qwen2.5-Max, it is much smarter and has much more creatitvity. Very soon, we are about to release the official version of QwQ-Max, and we will open-weight both QwQ-Max and Qwen2.5-Max under the license of Apache 2.0! Furthermore, we will also provide smaller variants, e.g., QwQ-32B, which can be deployed on local devices. Also, since a great number of users are expecting our APP, we are going to release an Android and iOS APP while we release our official QwQ-Max. Stay tuned for better things from Qwen!
English
131
459
2.7K
430.5K