Sign in Start free

Articles

Using AI in your business. Without the jargon.

Insights on AI automation, workflows and business process optimisation.

5 articles

Filtered by tag: #coding×

Cover image for Kimi K2.5 Deep Review: 100 AI Agents, 76.8% SWE-Bench, and $0.60/M Tokens — The Real Story

Kimi K2.5 Deep Review: 100 AI Agents, 76.8% SWE-Bench, and $0.60/M Tokens — The Real Story

Moonshot AI's Kimi K2.5 deploys up to 100 parallel sub-agents, scores 76.8% on SWE-Bench Verified, and costs $0.60/$3.00 per million tokens. We break down the benchmarks, the PARL training technique, and what actually works.Read →

Cover image for GLM-5.1 vs GPT-5.4 vs Gemini 3.1 Pro: Open-Source vs Proprietary for Coding (2026)

GLM-5.1 vs GPT-5.4 vs Gemini 3.1 Pro: Open-Source vs Proprietary for Coding (2026)

Side-by-side comparison of GLM-5.1 (open-source, MIT license) vs GPT-5.4 and Gemini 3.1 Pro for coding tasks. Benchmarks, pricing, and real-world tradeoffs as of March 2026.Read →

Cover image for GPT-5.4 Is Here: Everything Developers and Builders Need to Know

GPT-5.4 Is Here: Everything Developers and Builders Need to Know

AI coding agents productivity after eight months of real use

AI Coding Agents After 8 Months: From 25% to 90% AI-Written Code

A developer's real data after 8 months with AI coding agents — Claude Code went from writing 25% to 90% of all code.Read →

Cover image for GPT-5.2 and GPT-5.2 Codex Review: OpenAI's Best Model in 2026

GPT-5.2 and GPT-5.2 Codex Review: OpenAI's Best Model in 2026

GPT-5.2 is OpenAI's most powerful model yet with configurable reasoning from none to xhigh. We break down benchmarks, pricing, Codex features, and comparisons.Read →

Put it to work. In your business.

Describe what you need and Serenities builds it. Free to start, no credit card.

Start free — no credit card