long-context

Research

Study Reveals Limitations of RoPE in Long-Context AI Models, According to Preprint on arXiv
Byswgoettelman May 19, 2026

New study exposes RoPE’s theoretical limits in long-context AI models, challenging assumptions about Transformer scalability. Key findings on positional embedding failures published on arXiv.

Read More Study Reveals Limitations of RoPE in Long-Context AI Models, According to Preprint on arXiv
Research

DeepSeek Unveils V4 Open-Source Model With Long-Context Leap
Byswgoettelman April 28, 2026

DeepSeek drops V4: new open-source flagship with a major long-context leap. The Hangzhou lab keeps pressuring OpenAI, Anthropic & Google—and raises new questions about US chip export controls.

Read More DeepSeek Unveils V4 Open-Source Model With Long-Context Leap
Research

DeepSeek Unveils V4 Open-Source Model With Long-Context Leap
Byswgoettelman April 28, 2026

DeepSeek’s V4 open-source model brings a major long-context leap, intensifying US-China AI competition and raising new questions about chip export control effectiveness.

Read More DeepSeek Unveils V4 Open-Source Model With Long-Context Leap