alt Hacker NewsWe use GH Copilot at work and this week sat for a presentation by GH about optimizing token usage and maximizing ROI on tokens used. Anyone else get this presentation? They didn’t have time for questions because they had to run and give it to the next big enterprise on their list…
They basically said that everything is too expensive, you have to watch it like a hawk. It was as if they poured a bucket of cold water on the room. People were wondering how they could do anything faster with all these strategies. And then “sorry no questions. Bye!”
Replies
Did you have any good tips for optimizing usage?
The ones I’ve stumbled upon seem to be: switch models based on task complexity, use tooling like ASTs and compression, disable unused MCPs, compact often, be verbose with input to give clear guidance…
We did not have any presentation yet, but the first serious discussion about the cost of tokens has started on the documentation level. Looking forward to seeing these presentations!
> They didn’t have time for questions because they had to run and give it to the next big enterprise on their list…
This is such bullshit. Surely they could have recorded the shared part of the presentation and then spend all their time answering the questions?
Just hire people and pay then a fair wage and let everyone get richer together ffs
When did American capitalism become such a zero sum game
Interesting. We use Kiro here and looking at the public pricing subscriptions and it's benefit to my workflow, it is clearly a significant productivity increase per dollar spent. And we were told we have a signed a deal that is better than that public pricing. They recently just enabled overages on everyone's account so that people aren't throttled and they are shifting people up/down tiers as required behind the scenes to align with their actual usage.
However when the 'cost' to do something is relatively flat the cost/benefit analysis is going to depend on the value of the person being enabled. Someone making $60k a year using AI to gain a 20% output improvement may not be worth the cost but someone making $160k a year would.