2 min
Opus 5.5: Anthropic lowers the cost of working with its larger Claude
The larger Claude has new rates: $4 per million input tokens and $20 for output. Let’s look at what the claimed savings mean for longer jobs.
AI models and how to evaluate them: choosing, testing and comparing
How to choose a model for a task: Claude and OpenAI releases, comparisons on your own tasks, JEV (AI judging AI), RAG and local models.
Where to start
Start with the guide to comparing models on your own tasks, then try JEV and catch an error before you trust an answer.
Articles: AI models
News
2 min
Sonnet 5.5 replies faster. Token prices stay the same
Anthropic says Sonnet 5.5 generates responses more than 30 percent faster. Token rates stay unchanged; the claimed savings come from a shorter route to the result.
5 min
OpenAI DevDay 2026: a cheaper Sol, Dots and Codex with your laptop closed
Close your laptop and let Codex keep working. Add a cheaper Sol and Dots for recurring tasks, and there is plenty to unpack from DevDay. Here is where we would start.
Tutorials
5 min
Spot the mistake: you, JEV and GPT-6 Luna
The assistant quoted a ticket price. The trouble is, the source had no price list. We have twelve such situations: see how JEV, GPT-6 Luna and you judge them.
Guides
4 min
AI judging AI: what JEV can tell you about a model’s answer
One model answers; another judges it. Sounds sensible, until we ask who checks the judge. We take a look at JEV and share an exercise of our own.
2 min
Gemma 4 on your own hardware: from choosing a variant to a first app
Running a model on your own hardware sounds appealing. With Gemma 4, we start with one task, then look at variants, memory and everyday maintenance.
3 min
How to choose an AI model for working with your documents
Which model should you choose? Give both the same proposal and see what they do with the price, deadline and missing information. Time spent correcting them counts too.
3 min
Wrong RAG answers? Look at the passages used to write them
You upload the current policy, but the chat still gives the old terms. Before changing the model, let’s inspect the passages it actually received.