Two ways to stop trusting your AI provider on faith

Description and use

<p><em>Disclosure: I use both, and the links below are referral links — I may earn a reward if you sign up.</em></p> <p>Call a hosted model and you trust two things you can't check.</p> <p>One: the model on your bill is the model that answered. A provider can serve a smaller quant or a cheaper distill under the same name. You won't see it. Your agent gets a little worse and you blame your prompts.</p> <p>Two: where your prompt goes. Most gateways hand you a privacy policy. A policy is a promise about what a company says it will do. It is not a limit on what it can do.</p> <p>I build personal A

Problem

<p><em>Disclosure: I use both, and the links below are referral links — I may earn a reward if you sign up.</em></p> <p>Call a hosted model and you trust two things you can't check.</p> <p>One: the model on your bill is the model that answered. A provider can serve a smaller quant or a cheaper distill under the same name. You won't see it. Your agent gets a little worse and you blame your prompts.</p> <p>Two: where your prompt goes. Most gateways hand you a privacy policy. A policy is a promise about what a company says it will do. It is not a limit on what it can do.</p> <p>I build personal A

Outcome

<p><em>Disclosure: I use both, and the links below are referral links — I may earn a reward if you sign up.</em></p> <p>Call a hosted model and you trust two things you can't check.</p> <p>One: the model on your bill is the model that answered. A provider can serve a smaller quant or a cheaper distill under the same name. You won't see it. Your agent gets a little worse and you blame your prompts.</p> <p>Two: where your prompt goes. Most gateways hand you a privacy policy. A policy is a promise about what a company says it will do. It is not a limit on what it can do.</p> <p>I build personal A

Evidence

Two ways to stop trusting your AI provider on faith

Source