AI Glossary
What is Inference?
Training builds the model; inference uses it. Every chat reply, code completion, or generated image is inference. Its cost scales with model size and tokens processed, which drives the industry pattern of cheap small models for high-volume tasks and expensive frontier models for hard ones.
News momentum
Mentions in recent AI news titles and summaries, refreshed from the ingestion stream.
234
-17 vs prior 7d
- From LLM Inference to Agentic Workloads: Characterization and Implications
hn-ai · 1h
- OpenAI's Jalapeño chip beats Nvidia benchmarks
OpenAI reports its new Jalapeño chip offers 1.5-1.9x more AI work per watt and 1.7-3.6x low…
bluesky-ai · 9h
- Show HN: Launched free browser agent (the catch: ads)
hn-ai · 12h
- Darkbloom (AI inference on idle Macs) – security audit with PRs submitted
hn-ai · 15h