News for hackers. Stuff that matters.
Re:One month coding with GLM 5.3 Flash by gpugreg on Friday October 02, 2026 @03:26PM (#49937502)
How did you measure energy usage?

Edit: I found a linked article that mentions the inference provider who does the measurements.

Re:One month coding with GLM 5.3 Flash by ThibWeb on Friday October 02, 2026 @03:34PM (#49937602)
Yes, all from Neuralwatt, GPU energy use only. Makes models’ “efficiency” much more visible than tokens.