The home for great developer writing.

We surface the best developer writing from thousands of independent blogs, updated daily.

I'm (mostly) picking models on speed now, not intelligence

· Martin Alderson · Aug. 2, 2026, 1:04 a.m.

Machine Learning productivity AI Models Performance Metrics

Summary

Martin Alderson discusses his shift in evaluating AI models based on speed (tokens per second) rather than raw intelligence, suggesting that higher speed may become more critical than intelligence in the future of AI model selection.

Read full post on martinalderson.com →

MORE POSTS LIKE THIS

Try the very fast models

Natemeyvis · Jul 27, 2026

future of work Generative AI

Claude Fable 5.2 and Mythos 5.2: Power, Price and Limits

Aleksei Aleinikov · Nov 11, 2026

claude-fable-5-2 claude-mythos-5-2

Agentics: agent evals considered harmful

theahura · Oct 22, 2026

Machine Learning software development

10 AI Agent Terms I Wish I’d Known Before Building My First Agent

Roberto · Oct 9, 2026

artificial-intelligence Technology

Jev: Decision Models on Trial

Blogs Cisco · Oct 5, 2026

Artificial Intelligence (AI) AI Security

Looking for a vision replacement for GPT-5-mini

Community Openai · Oct 5, 2026

Machine Learning image recognition

Discover more posts →

AUTHOR