AI Tools & Models HOTFeaturedAll
#prompt

#prompt

11 items · All topics →

AWS Machine Learning BlogNewScore85

Use prompt caching with open-weight models on Amazon Bedrock

On Bedrock, prompt caching lets open-weight models reuse the long context that generative AI apps otherwise resend with every request, cutting input costs and latency.

Nov 16, 23:42

Why this: Official source · Covers model and prompt · Published within 24 hours

arXiv cs.AIScore65

Graph Your Own Prompt

This work proposes graph consistency regularization, injecting relational graph structures derived from model predictions into prompts to make prompt optimization more stable and reliable.

Nov 16, 13:00

Why this: Covers model and prompt · Relevant to this topic

OpenAI NewsScore75

At Holiday Extras, dots get to work before anyone asks

At Holiday Extras, OpenAI's dots push out launch reports on their own, point out issues that might slip by, and even talk through upcoming meetings during the commute.

Nov 16, 08:00

Why this: Official source · Covers prompt

Simon WillisonScore75

datasette-agent 0.6a0

datasette-agent 0.6a0 is Datasette's agent plugin for asking questions about your data, and this release adds an agent prompt directly in the interface.

Nov 15, 11:49

Why this: Covers Agent and prompt · Relevant to this topic

AWS Machine Learning BlogScore70

Four Amazon Bedrock inference choices that affect cost

Your bill can keep climbing even after prompts and app logic are tuned, because four per-request settings — max tokens, reasoning effort, service tier, and cache duration — all move the cost.

Nov 13, 04:51

Why this: Official source · Covers inference and prompt

Simon WillisonScore60

Quoting Prompting Claude Fable 5.2

Claude Fable 5.2 is sensitive to who owns the code it touches — in Anthropic's small-task tests, it defaulted to building on existing structure when the prompt left ownership unmentioned.

Nov 10, 13:34

Why this: Covers model and Claude · Relevant to this topic