Story
The session you cannot take with you
1 report
1 website
1 discussion
Latest report
Overview
Inference APIs allow users to send input and receive output, facilitating conversation archiving and replaying. However, challenges such as prompt cache storage on external GPUs, differing tokenization between models, and intentional sampling unreproducibility complicate session portability.
Summary from earendil.com.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · earendil.com
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-07-31.
- Praise: This article gives a very good overview of a problem that most users of AI rarely evaluate, highlighting important issues with provider lock-in and user experience.
- Praise: I'm optimistic that dark patterns will eventually be replaced by more respectful practices in AI, as the market matures and user awareness grows.
- Praise: Many commenters are finding innovative ways to maintain context across sessions, suggesting a creative push towards better user experience in AI interactions.
- Concern: If switching models is painful, providers can create vendor lock-in, enshittify the user experience, and drive up costs — this is a huge concern for future competition.
- Concern: The coupling of powerful extensions with inference APIs creates unnecessary barriers, limiting user freedom and innovation.
- Concern: Some models are overly verbose, resulting in poor signal-to-noise ratios that frustrate users and hinder productivity.