Live data from Hacker News

Ask HN: Corporate Disconnect Between "Tokenmaxxing" and Token Optimization

news.ycombinator.com

11–12 of 12 posts

Re: Ask HN: Corporate Disconnect Between "Tokenmaxxing" and Token Optimization

#11

> Is anyone else going through this I thought this became the norm already, isn't the whole industry working in the same way at the moment?

You think not being allowed to write any code manually is the norm?

Re: Ask HN: Corporate Disconnect Between "Tokenmaxxing" and Token Optimization

#12
Ok so disclosure first I have made a product for exactly this problem. But the answer isn't agents, skills although those do help it's an auto switching layer that chooses model automatically according to the goals. But yes this tug of war is the reason I did build it. Went down 40-50% tokens with much higher usage.

But this is headed to some kind of a reckoning. One comment about Gartner's hype cycle seems to be the best. In months the narrative has shifted from who needs devs to AI costs are uncontrollable. Both false but on opposite ends

Post reply on HN