Matt Bandy
@matthewbandy.bsky.social
AI/ML. Drones, imagery, computer vision. Ecology and archaeology. Tortoises. Early farmers. Distance sampling. Linux, Python, R. Recently, NetHack.
This is a report of my personal experience, not a formal evaluation. I thought that was clear.
June 21, 2026 at 1:41 PM
This is a report of my personal experience, not a formal evaluation. I thought that was clear.
Performance evaluation is subjective, using the models for my own work, mainly software development. Cost is openrouter token cost: openrouter.ai/compare/anth.... Claudish is Claudish: claudish.com
Claude Opus 4.8 vs GLM 5.2 vs Gemini 3.1 Pro Preview - AI Model Comparison
Compare Claude Opus 4.8 from Anthropic, GLM 5.2 from Z.ai, and Gemini 3.1 Pro Preview from Google on key metrics including benchmarks, price, context length, and other model features.
openrouter.ai
June 21, 2026 at 1:40 PM
Performance evaluation is subjective, using the models for my own work, mainly software development. Cost is openrouter token cost: openrouter.ai/compare/anth.... Claudish is Claudish: claudish.com
Awesome, thanks!
November 20, 2023 at 11:34 PM
Awesome, thanks!
Have you read the Books of Babel yet? The first is "Senlin Ascends."
November 20, 2023 at 9:07 PM
Have you read the Books of Babel yet? The first is "Senlin Ascends."