Unverified50% confidenceBenchmarkExact time
Changing the intent distribution from Zipf-skewed to uniform, the cost reduction for Sonnet and Haiku drops from 70% to 56%; if all 3000 questions are different, the reduction is only 38%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedThe compute cost per unit of inference is declining at a rate of 40% to 60% per year.64% similarUnverifiedWhen the driver pool expands from 10 to 45 drivers, TEMPEST drops by only 4.3 percentage points, while the supervised triplet-loss baseline drops by 22 percentage points and the unsupervised triplet-loss baseline drops by 32.5 percentage points.63% similarUnverifiedQwen 3.8 is slower than 3.6, with prefill and inference speeds dropping by approximately 40% and 20% respectively.63% similarUnverifiedWhen the BiLSTM was constrained to a parameter budget matching the quantum model, its performance dropped significantly, with mean average precision (MAP) falling by 3.63 percentage points.60% similarUnverifiedAnthropic's experiments showed that combining embedding with BM25 and adding context to chunks reduced the top-20 retrieval failure rate by 49% (from 5.7% to 2.9%).60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065412API
curl https://kongchang.com/api/v1/knowledge/claims/1065412MCP
get_claim(id=1065412)