Tag
23 articles
DeepSeek has released DeepSeek-V4.1-Flash-1017, a performance-enhanced model scoring 77.0 on DeepSWE, alongside a new Search API for developers.
Learn how DeepSeek Harness v0.2 brings powerful AI tools to your desktop with new features like plugin managers, code review, and automation tasks.
This article explains the concept of KV cache in AI models and how the new DeepSeek V4.1-Flash model reduces memory needs to make AI more efficient and affordable.
Learn how DeepSeek-V4.1-Flash improves AI processing of long inputs using memory-saving techniques like FP4 KV caching and attention reuse.
DeepSeek AI has released DeepSeek Harness v0.1, a developer preview agent harness where every capability is a Cordis plugin, under the MIT license.
Alibaba launches Qwen3.8-Max, while DeepSeek's V4-Flash model gains traction for its low inference costs, highlighting a growing trend toward affordable AI in China.
Chinese AI startup DeepSeek has paused its second funding round after leaked comments from founder Liang Wenfeng went viral on social media, raising concerns about transparency and leadership.
A Chinese luggage maker's stock filing has revealed that DeepSeek, a Hangzhou-based AI startup, is valued at approximately $52 billion, marking a significant milestone in the AI industry's growing recognition of the company's potential.
This article explains how AI companies like DeepSeek raise money quickly to fund their expensive AI development, including data centers and custom chips.
DeepSeek introduces peak-hour surge pricing for its V4 models, challenging the AI price war dynamics in China.
China's AI sector is experiencing a funding surge, with DeepSeek raising $7.4 billion in its first-time funding round, signaling a strategic push for self-reliance amid global trade tensions.
Learn how DSpark, a new AI framework from DeepSeek, speeds up text generation in AI models by making smart guesses and verifying only when necessary, without sacrificing accuracy.