TokenPowerBench: Benchmarking the Power Consumption of LLM Inference · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2512.03024/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTTokenPowerBench: Benchmarking the Power Consumption of LLM Inference — mentioned by marcyb5sthttps://news.ycombinator.com/item?id=48382414urn:hackerpapers:mention:2512.03024:48382414Wed, 03 Jun 2026 11:09:26 GMT<p>I think you are assuming cost per task will become cheaper and that there is unlimited energy supply. While tokens costs are going down, the number of token burned is going up and up. Case in point Sam Altman is complaining about their top token users burning through 100B tokens per month [1]. So you have token prices going down but token usage going up 10x per year (if you extrapolate linearly from what Sam was ranting about). This is happening because people trust more and more LLMs and give them more autonomy and more complex tasks (IMHO). So if you really need a true unsupervised agent…</p><p><a href="https://hackerpaper.kaipfister.de/p/2512.03024/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG