📰 Dev.to · AI Tech Connect

5 articles · Updated every 3 hours · View all reads

All Articles 66,892 Blog Posts 99,724 Tech Tutorials 16,149 Research Papers 13,808 News 12,510 ⚡ AI Lessons

31% in Production, 37% Gap: Real Enterprise AI Agent Numbers

Dev.to · AI Tech Connect 15h ago

31% in Production, 37% Gap: Real Enterprise AI Agent Numbers

80% of Q1 2026 apps embed an agent, but only 31% have one in production. The buyer-side playbook for enterprise AI agent evaluation.

Zyphra's ZAYA1-8B: An Open MoE Trained End-to-End on AMD

Dev.to · AI Tech Connect 5d ago

Zyphra's ZAYA1-8B: An Open MoE Trained End-to-End on AMD

Apache 2.0 MoE with 8B total / 760M active parameters, trained entirely on AMD Instinct hardware — the first credible no-NVIDIA frontier training story.

Qwen3.6-27B: The 27B Model That Beats a 397B MoE on Coding

Dev.to · AI Tech Connect 1w ago

Qwen3.6-27B: The 27B Model That Beats a 397B MoE on Coding

Alibaba's Qwen3.6-27B outperforms the 397B Qwen3.5 MoE on agentic coding benchmarks. Apache 2.0, fits on a single A100 — the self-hostable frontier coding agent

Cut LLM API Costs 70–90%: Layered Caching in Production

Dev.to · AI Tech Connect 2w ago

Cut LLM API Costs 70–90%: Layered Caching in Production

A three-tier caching stack — exact match, semantic similarity, provider-level prompt cache — that compounds to 70–90% spend reduction, with real production hit

Context Window Engineering: Reliable Recall at 1M Tokens

Dev.to · AI Tech Connect 2w ago

Context Window Engineering: Reliable Recall at 1M Tokens

Why 'lost in the middle' degrades recall past ~20k tokens and how to fight it with XML markers, hierarchical processing, and server-side compaction on Claude, G