Token spend breaks budgets – what next?(newsletter.pragmaticengineer.com) |
Token spend breaks budgets – what next?(newsletter.pragmaticengineer.com) |
No mention anywhere of context engineering (starting a new session once a task is done, using sub-agents, reducing context for MCPs), and it seems some companies are actually rewarding developers for wasting token, instead of being smart.
I think companies dream of increasing productivity using AI, so they want to encourage their devs to use AI more. Since it's notoriously very hard to measure software productivity, and they have no way to really measure how well engineers use AI, they measure number of tokens.
Which is dumb. Because a bad engineer might ask the AI to "convert this CSV to JSON" which would burn token, while a good engineer would ask the AI to "write a script to convert this CSV to JSON". Of course, this example is not ideal, since a SOTA model would probably just write a script anyway in the first case... But you get the idea.