MarkTechPost - 2026-06-17
4 items collected.
1. Vercel Releases Eve: An Open-Source AI Agent Framework Where Each Agent is a Directory of Files Mapped to Capabilities
Author: Asif Razzaq
Published: 6/17/2026, 5:22:51 PM
Categories: Agentic AI, Editors Pick, New Releases, Open Source, Python, Software Engineering, Staff, Tech News, Technology
Vercel has open-sourced eve, an Apache-2.0 agent framework now in public preview. An agent is a directory of files, with durable execution, sandboxes, approvals, connections, channels, and evals built in. Scaffold with npx eve@latest init and deploy unchanged via vercel deploy. The post Vercel Relea...
2. MiniMax Sparse Attention (MSA): a Two-Branch Block-Sparse Attention Trained on a 109B-Parameter MoE With a 3T-Token Budget
Author: Asif Razzaq
Published: 6/17/2026, 7:44:54 AM
Categories: Agentic AI, AI Infrastructure, AI Paper Summary, AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Machine Learning, New Releases, Software Engineering, Staff, Tech News, Technology
MiniMax released MSA, a sparse attention built on Grouped Query Attention. A lightweight Index Branch selects Top-k key-value blocks per query and GQA group; the Main Branch attends only to those blocks. It matches GQA on downstream benchmarks while reducing per-token attention compute 28.4× at 1M c...
3. OpenAI’s Deployment Simulation Extends Pre-Deployment Risk Assessment to Agentic Coding Through Simulated Tool Calls
Author: Michal Sutter
Published: 6/17/2026, 5:49:54 AM
Categories: Agentic AI, AI Infrastructure, AI Shorts, Artificial Intelligence, Editors Pick, Software Engineering, Staff, Tech News, Technology
OpenAI introduced Deployment Simulation on June 16, 2026. The method replays past conversations through a new candidate model before release. It then grades the completions to estimate deployment-time rates of undesired behavior. We break down how the pipeline works, the reported 1.5x median multipl...
4. How to Build Memory-Efficient Transformers with xFormers Using Packed Sequences, GQA, ALiBi, SwiGLU, and Causal Attention
Author: Sana Hassan
Published: 6/17/2026, 12:02:25 AM
Categories: Deep Learning, Editors Pick, Machine Learning, Staff, Technology, Tutorials
We implement xFormers, a practical toolkit for fast, memory-efficient Transformer models on GPUs. We validate memory-efficient attention against a standard implementation, then compare speed and memory across sequence lengths. We work through causal masking, packed variable-length sequences, grouped...