The AI Safety Measurement Problem: What We Can't Test, Trust
Prijzen vanaf
21,00
Uitgelicht
|
21,00 |
Naar shop
|
|
54,99 |
Naar shop
|
|
54,99 |
Naar shop
|
| VERGELIJK ALLE AANBIEDERS (3) | ||
Beschrijving
Bol
A safety claim about an AI system is only as credible as the measurement that backs it. Everything else in this book follows from that sentence. If a developer says a model is "safe enough to deploy," a regulator says it is "low-risk," or a buyer says it is "fit for purpose," each of those statements is a load-bearing claim about behavior under ...
Beschrijving
(2)
Bol
A safety claim about an AI system is only as credible as the measurement that backs it. Everything else in this book follows from that sentence. If a developer says a model is "safe enough to deploy," a regulator says it is "low-risk," or a buyer says it is "fit for purpose," each of those statements is a load-bearing claim about behavior under ...
AmazonPagina's: 178, Paperback, W. Frederick Zimmerman
Productspecificaties
Prijshistorie
* Prijshistorie bevat geen data van Amazon, Amazon Marketplace.
Prijzen voor het laatst bijgewerkt op:
Gerelateerde resultaten
Uitgelichte Keuze
21,00
