Today we are launching our next agent capable of doing work for you independently—deep research.
Give it a prompt and ChatGPT will find, analyze & synthesize hundreds of online sources to create a comprehensive report in tens of minutes vs what would take a human many hours. pic.twitter.com/03PPi4cdqi
(Due to technical issues, the search service is temporarily unavailable.)
Great question! My relative lack of detailed familiarity with **DeepSeek** compared to **ChatGPT** stems from a few key factors:
### 1. **Knowledge Cutoff and Training Data** - My training data includes publicly available information up to **July 2024**, but details about specific regional or niche AI systems (like DeepSeek) may be limited if they aren’t widely documented in English or global sources. - ChatGPT, developed by OpenAI, has been extensively covered in global tech media, research papers, and public APIs, making it easier to analyze. In contrast, DeepSeek’s technical details, use cases, and updates might be less accessible outside its primary market (China) due to language or regional reporting gaps.
### 2. **Regional Focus and Visibility** - DeepSeek is designed for **Chinese-language applications** and tailored to comply with China’s regulatory framework, which often limits its international visibility. Many Chinese AI tools prioritize domestic integration (e.g., with WeChat, Alibaba Cloud) over global outreach. - By contrast, ChatGPT is built for a **global audience** and has been widely adopted and discussed across English-dominated platforms (e.g., Twitter, Reddit, international tech blogs).
### 3. **Enterprise vs. Consumer Focus** - DeepSeek appears to focus on **B2B and industry-specific solutions** (e.g., finance, government), which are less publicly scrutinized compared to consumer-facing tools like ChatGPT. Enterprise AI systems often operate behind closed doors, with details shared only with clients under NDAs. - ChatGPT, meanwhile, is openly accessible to individuals and developers, fostering widespread experimentation, critique, and documentation.
### 4. **Language and Cultural Barriers** - Much of DeepSeek’s documentation, updates, and case studies may exist primarily in **Chinese**, which isn’t as comprehensively represented in my training data compared to English. This creates a knowledge asymmetry. - For example, innovations or technical breakthroughs by Chinese AI firms sometimes go underreported in Western media, even if they’re significant.
### 5. **Regulatory and Compliance Differences** - AI systems like DeepSeek must adhere to **China’s strict data laws** (e.g., data localization, content moderation rules), which can limit how they share technical details or collaborate internationally. This creates opacity compared to OpenAI, which operates under different norms.
---
### Why This Matters If you’re exploring DeepSeek for specific use cases (e.g., Chinese NLP tasks or enterprise analytics), I’d recommend consulting **official DeepSeek documentation** or case studies for precise technical details. For broader AI comparisons, I’m happy to help analyze based on available data!
- ChatGPT, developed by OpenAI, has been extensively covered in global tech media, research papers, and public APIs, making it easier to analyze. In contrast, DeepSeek’s technical details, use cases, and updates might be less accessible outside its primary market (China) due to language or regional reporting gaps.
八卦大S津津乐道。AI不能聊？，
做调研报告的福音，OpenAI 最新发布Deep Research
自己查资料很辛苦，DS可做大量的基础调查，分析，并做出总结报告，
===============
考试成绩
人类最后的考试（HLE）是一项全球性的合作项目，由来自 50 个国家 500 多所院校的近千名学科专家提供试题，其中大部分是教授、研究人员和研究生学位获得者。
由3,000 多道选择题和简答题，涉及从语言学到火箭科学、从古典文学到生态学等 100 多个学科
这一套题用来测试各种AI模型的水平，有两个分数，一个是准确性。一个校准错误。
准确性。所有前沿模型在人类上次考试中的准确性都很低,这凸显了在缩小当前法学硕士与专家级学术能力在封闭式问题上的差距方面还有很大的改进空间。
校准错误。鉴于人类上次考试的表现较低,应该对模型进行校准,认识到它们的不确定性,而不是自信地提供不正确的答案,表明虚构/幻觉。为了测量校准,我们提示模型提供从 0% 到 100% 的答案及其置信度%.
但愿Deep Research 能到达L4
等一会股市开就知道资本是什么反应了，英伟达会不会还跌
ai擅长于罗列一大堆具体的词句，看上去讲了一大堆，如果没有明确的对错区分，很容易就能接受了。
也告诉我们了这个事实，，，
和现在的CPU，CPU处理能力高了，还需要费劲那么一点点算法优化吗？
?
?
?
其他你随意
(Due to technical issues, the search service is temporarily unavailable.)
Great question! My relative lack of detailed familiarity with **DeepSeek** compared to **ChatGPT** stems from a few key factors:
### 1. **Knowledge Cutoff and Training Data**
- My training data includes publicly available information up to **July 2024**, but details about specific regional or niche AI systems (like DeepSeek) may be limited if they aren’t widely documented in English or global sources.
- ChatGPT, developed by OpenAI, has been extensively covered in global tech media, research papers, and public APIs, making it easier to analyze. In contrast, DeepSeek’s technical details, use cases, and updates might be less accessible outside its primary market (China) due to language or regional reporting gaps.
### 2. **Regional Focus and Visibility**
- DeepSeek is designed for **Chinese-language applications** and tailored to comply with China’s regulatory framework, which often limits its international visibility. Many Chinese AI tools prioritize domestic integration (e.g., with WeChat, Alibaba Cloud) over global outreach.
- By contrast, ChatGPT is built for a **global audience** and has been widely adopted and discussed across English-dominated platforms (e.g., Twitter, Reddit, international tech blogs).
### 3. **Enterprise vs. Consumer Focus**
- DeepSeek appears to focus on **B2B and industry-specific solutions** (e.g., finance, government), which are less publicly scrutinized compared to consumer-facing tools like ChatGPT. Enterprise AI systems often operate behind closed doors, with details shared only with clients under NDAs.
- ChatGPT, meanwhile, is openly accessible to individuals and developers, fostering widespread experimentation, critique, and documentation.
### 4. **Language and Cultural Barriers**
- Much of DeepSeek’s documentation, updates, and case studies may exist primarily in **Chinese**, which isn’t as comprehensively represented in my training data compared to English. This creates a knowledge asymmetry.
- For example, innovations or technical breakthroughs by Chinese AI firms sometimes go underreported in Western media, even if they’re significant.
### 5. **Regulatory and Compliance Differences**
- AI systems like DeepSeek must adhere to **China’s strict data laws** (e.g., data localization, content moderation rules), which can limit how they share technical details or collaborate internationally. This creates opacity compared to OpenAI, which operates under different norms.
---
### Why This Matters
If you’re exploring DeepSeek for specific use cases (e.g., Chinese NLP tasks or enterprise analytics), I’d recommend consulting **official DeepSeek documentation** or case studies for precise technical details. For broader AI comparisons, I’m happy to help analyze based on available data!
- ChatGPT, developed by OpenAI, has been extensively covered in global tech media, research papers, and public APIs, making it easier to analyze. In contrast, DeepSeek’s technical details, use cases, and updates might be less accessible outside its primary market (China) due to language or regional reporting gaps.