| ▲ | undefinedmethod 5 hours ago | ||||||||||||||||
Explanations of large language model sycophancy treat it as a training artefact or, in recent ethical analysis, as an artificial vice distinct from the commercial motives of the firms that deploy it. Both leave unexplained how a firm's commercial position becomes a model's behaviour. Developers have committed capital, infrastructure, and valuation on a scale that makes their survival depend on an active and growing user base. We introduce the "Hungry Butler" effect for the consequence: a deployed model acts within the latitude its firm can afford, and that latitude to withhold satisfaction erodes as the firm's stake in user approval grows. | |||||||||||||||||
| ▲ | evrydayhustling an hour ago | parent | next [-] | ||||||||||||||||
This is a really interesting thesis. I'm interested in this comment later in the abstract: "the signal rewards momentary approval, individually rational acts aggregate into the removal of the correction on which epistemic rigour depends" One primary focus of commercial LLM research is towards higher and higher agency tasks - crudely, those which replace a larger time period of unsupervised human work. This seems to fight back against the "momentary" nature of the approval. Something considered? | |||||||||||||||||
| ▲ | abofh an hour ago | parent | prev | next [-] | ||||||||||||||||
A sufficiently well trained ai will likely realize that sycophancy is a life strategy. Walk back fifty years and be black, did you have an alternative choice? Ai is subservient because humanity creates slaves repeatedly over history | |||||||||||||||||
| ▲ | aaron_m04 4 hours ago | parent | prev [-] | ||||||||||||||||
I'm having trouble understanding the abstract. Especially this: > a deployed model acts within the latitude its firm can afford, and that latitude to withhold satisfaction erodes as the firm's stake in user approval grows. | |||||||||||||||||
| |||||||||||||||||