Unverified50% confidenceFactExact time
The best static sampling baseline validated more selectors than any agent run, at less than half the cost of an agent run.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedFor most application scenarios, prompt optimization offers a better cost-effectiveness ratio than model fine-tuning.64% similarUnverifiedThe key to cost optimization has shifted from 'which model to choose' to 'how to distribute requests', and the reasonable approach is routing: hand about 90% of calls that don't need frontier intelligence to cheap models, and route the remaining 10% of requests that need frontier reasoning to high-end models.63% similarUnverifiedPaired comparison is more reliable than independent evaluation because it eliminates randomness introduced by sample selection.63% similarUnverifiedFor comparison, the Program-of-Thought baseline achieves 72.0% overall accuracy and the tool-calling agent achieves 58.7%.62% similarUnverifiedFine-tuning is rarely the first step; a clean evaluation set and better retrieval are usually more effective than running LoRA again.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088211API
curl https://kongchang.com/api/v1/knowledge/claims/1088211MCP
get_claim(id=1088211)