The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain Problem · HackerPapers discussions

The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain Problem — HN submission

Tue, 01 Sep 2026 12:33:01 GMT

Show HN: Throttling AI models under load can backfire and increase demand (SIM)

OP here: TL-DR: When AI providers silently swap weaker models under high demand, this can cause even more demand as users tend to re-ask. This is even worse for agents. Both of these effects cause even higher load on the data centers. I guess all of us have felt when the models "don't feel quite the same", so this could explain part of it. I modeled this as a fleet scheduling problem using Queueing Theory and Dynamic Programming over a finite horizon. The standard practice of throttling once the number of jobs in server exceeds certain threshold is in fact suboptimal. The optimal policy…

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain Problem — HN submission

Fri, 28 Aug 2026 12:35:22 GMT

Show HN: I built a tool showing how AI providers (should) throttle their models

OP here: this project was born out of the frustration/paranoia that AI providers are throttling their models when their server load is too high. So, I set out to model and study the problem mathematically to understand what was happening, what I found was quite surprising. The idea seems natural: as the data center demand increases momentarily through the day, throttling their models (either using quantized versions, reducing the context window or lowering the tier of the model to a smaller one) seems appealing as the replacement model in principle uses less electricity. The problem is that…

6 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain Problem — HN submission

Wed, 26 Aug 2026 13:08:39 GMT

Show HN: I built a tool showing how AI providers (should) throttle their models

OP here: this project was born out of the frustration/paranoia that AI providers are throttling their models when their server load is too high. So, I set out to model and study the problem mathematically to understand what was happening, what I found was quite surprising. The idea seems natural: as the data center demand increases momentarily through the day, throttling their models (either using a quantized version, reducing the context window or lowering the tier of the model to a smaller one) seems appealing as the model in principle uses less electricity. The problem is that this can…

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.