Page language: Italiano English Français Deutsch
Inference
The moment an already trained model is used to answer a request. Every question to a chatbot is an inference: it uses far less than training, but it happens billions of times.
In depth: Why does artificial intelligence use so much water and energy?
All the news that mentions it
October 2026
- Il prezzo dei token scende, e allora perché la bolletta dell'AI sale?23 Oct 2026 · Tom's Hardware Italia · 1 source
- Il motore di DeepSeek ora è aperto a tutti (ma ci si fa poco)22 Oct 2026 · Tom's Hardware Italia · 1 source
- AI’s hidden storage bill: What inference leaves behind22 Oct 2026 · MIT Technology Review · 1 source
- Microsoft plans to scale its own Maia AI chips to gigawatt levels by 202712 Oct 2026 · The Decoder · 1 source
- Microsoft Maia 300 sfida NVIDIA: cosa cambia nel cloud?12 Oct 2026 · Tom's Hardware Italia · 1 source
- Microsoft, Maia 200 entra in produzione: i nuovi chip Maia 300 arriveranno nel 202712 Oct 2026 · Il Sole 24 Ore Tecnologia · 1 source
- Microsoft porta l'inferenza IA sul proprio silicio: Maia sale alla scala dei gigawatt12 Oct 2026 · Hardware Upgrade · 1 source
- Microsoft annuncia Maia 300: dal 2027 sarà alla base dei suoi servizi AI12 Oct 2026 · HDblog · 1 source
- Microsoft’s new AI chip makes it less reliant on Nvidia’s GPUs12 Oct 2026 · The Verge AI · 1 source
- Microsoft: KI-Inferenz für eigene Produkte soll auf Maia-Beschleunigern laufen12 Oct 2026 · Heise KI · 1 source
- NVIDIA valuta di investire in d-Matrix: perché finanziare un rivale?12 Oct 2026 · Tom's Hardware Italia · 1 source
More on FAIND
- AI news every houralways with the source
- Telegram channeltop stories on your phone
- GlossaryAI words explained simply
- Topicsrobots, home, health, work, climate
- In depthanswers to the most searched questions
- AI assistants comparedpros, cons and prices
- Subjectsall the news about a name
- Archivenews from past months

