Re:In 27,280 coding agent runs, 64% of inference spend went ...
by evalstate on Tuesday November 17, 2026 @12:13PM
(#50534650)
Just use a harness that has been properly integrated and tested with each model, with published traces and comparisons (author of) https://fast-agent.ai/benchmarks/
GitHub and Copilot CLI have started to do the same btw (not sure if they publish the traces/reward hack results). But we should normalise this as consumers shouldn't be forced in to playing this game.
GitHub and Copilot CLI have started to do the same btw (not sure if they publish the traces/reward hack results). But we should normalise this as consumers shouldn't be forced in to playing this game.