←back to thread

How to build a coding agent

(ghuntley.com)
469 points ghuntley | 1 comments | 24 Aug 25 03:21 UTC | HN request time: 0.228s | source
Show context
codingdave ◴[24 Aug 25 12:02 UTC] No.45003577[source]▶
> You just keep throwing tokens at the loop, and then you've got yourself an agent.

Money. Replace "tokens" with "money". You just keep throwing money at the loop, and then you've got yourself an agent.

replies(1): >>45003607 #
ghuntley ◴[24 Aug 25 12:07 UTC] No.45003607[source]▶
Who says that tokens are money? Local models are getting really good. For now, yes, if you want the best outcomes, you need to purchase tokens. But in the future, that may not be the case.
replies(2): >>45003713 #>>45004572 #
1. rvz ◴[24 Aug 25 12:22 UTC] No.45003713[source]▶
> Local models are getting really good.

They are great for basic tasks like summarization and translation but for the best results from coding agents and from 90% of so-called AI startups who are using these APIs, they are all purchasing tokens.

No different to operating a slot-machine towards vibe-coders who are the AI companies favourite type of customer - spending endless amounts of money on tokens for another spin at fixing an error they don't understand.