Hacker News Reader

Comment by brian-armstrong | Hacker News Reader

I read these stories and I can never figure out how people are managing to use these $200 plans. If I really go full bore, I can sometimes max out the $20 plan. Even then, it already produces more code than I can reasonably review and merge.

View on HN

I've maxed out my chatgpt plus the first week and that include an smf forum rewrite. Trying my best I haven't been able to max out again. Things are setup that you need to max out your 5 hour window multiple times which becomes a job in itself.

At work I'm struggling to keep my claude bill around $500.

Simple: a lot of the people claiming they’re reviewing the output of these models are lying.

Also if you run the “loops” they’re now yapping about, it will burn through enormous amounts of usage as well.

I can't even keep up with the chain of thought needed to manage a single session, let alone review. I typically never exceed 30% of a 5x plan. Fable took me almost to the limits, but not Opus. Claude design hits things harder, but still not to saturation.

Exactly this, it’s the loops. The first 50k tokens of a task is by far the most valuable. But when left to run independently, the agent will consume millions of tokens of error messages from running tests and discovering a minor syntax error, a missing import, a method call with incorrect parameters, etc. Then it will write some helper program while debugging the main task and get into the same loop debugging minor errors in the helper. From my experience, the vast majority of tokens consumed by Claude Code on totally independent tasks are consumed fixing minor mistakes it just made.

do you do it for a job (8 hours a day)? and do you work in large, mature projects (more than 5 team members)? A big part of it is dealing with frankly terrible architecture and 15 people's different ideas of how things should work (and the spam theyve been able to do with their own agents makes this worse)

Reply on news.ycombinator.com