After spending some time on how Claude code (leaked) tools were written, it makes sense why we constantly hit limits, for all the amazing llm capabilities, CC does not have edit tool and always read before write ( this makes sense) but I expected some surgical precision magic software, seems like other agents like master open code and pi are way better than CC in taken usage
Claude Code users hitting usage limits 'way faster than expected'
241–245 of 245 posts
Re: Claude Code users hitting usage limits 'way faster than expected'
#242[dead]
Re: Claude Code users hitting usage limits 'way faster than expected'
#243Earlier quoted context omitted.
Once you get used to using claude as an abstraction layer you start getting pretty reckless with it. My organization has the concept of "premium models" where our limits reset every month. I hit my limit pretty quickly last month because I was burning tokens doing things that would have been a simple bash loop in the past - all because I was used to interfacing with Claude at the chat layer for all my automation need…
This is a real danger that I think a lot of people will run into as prices go up more and more in the future. Completely outside of the productivity debate, offloading cognitive tasks to LLMs leaves you less practiced in them and less ready to do them when the LLM isn't available. When you have to delegate only certain tasks to the LLM for financial reasons, you may find yourself very frustrated.
do you think we're already seeing mental atrophy play out?
or do you think model inference/training will get cheap that we won't reach the point of "high prices"?
Re: Claude Code users hitting usage limits 'way faster than expected'
#244The only way AI will be profitable to companies like Anthropic or OpenAI is to make the cost $1000-2000/month or more for coding. Every programmer will be forced to pay for it because it's only a fraction of their salary (in the US anyway) and it's the only way the programmer will be competitive. Whether the company pays for it, or they pay for it themselves, it will need to be paid. There's no other way that these c…
> the cost $1000-2000/month or more for coding. Every programmer will be forced to pay for it because it's only a fraction of their salary (in the US anyway) and it's the only way the programmer will be competitive. I routinely match or beat Claude with regards to speed, I often race it to the solution because Claude just takes so long to produce a usable result. Staying competitive doesn't mean only paying an AI for…
Amen! I have had this funny feeling of mental atrophy all along. I'm working at a company that wants us to be "ai-native".
The amount of ai slop from diffs and posts is nauseating.
Re: Claude Code users hitting usage limits 'way faster than expected'
#245Definitely hitting limits insanely faster. Not sure if it's the same problem for everyone or they're cranking up usage for low users to support others. I do bursts of work and a month ago would write a lot of code every window and then pause for reset using mix of chat and CLI. Currently ran a excel work session with code, burnt a lot. Asked it to give me a view on how to optimise excel work to burn less, got a 2 paras of answer burning 9% of session and i copy-pasted those two paras into Chat since it usually cost me less to plan there, asked it to help me figure out best way to set this up - 11% burnt for a couple of bullet point options. Has never happened so fast.
This is a massive shift from my previous experience.