That’s such a depressing way to see things. I’m sure most people do something they don’t utterly despise, is only because they select for their local optimum.
If you live in the bubble where you experience this, congratulation you live a wonderfully privileged life, never interact with anyone or are totally oblivious to the experiences of all the people you interact with on a daily basis.
But also, many people choose to do something they hate so they earn more money. They could be just as privileged and choose not to, just so they can compete with the Joneses and consume more...
I hate doing laundry and cleaning dishes. I still do it, though.
There are things in life that you won't enjoy but you need to do. Learning to do them anyway is in fact a life skill.
I've seen people follow their dreams into careers they chose because they wanted them, despite those careers not being paid well. They're all at least as miserable as the average person, because what they enjoyed is now work, and they don't have money for anything they now enjoy.
"Do whatever makes you happy" is a life plan for the financially independent. Most people simply don't have that luxury.
Parenting, having and raising children, including but not limited to the act of giving birth is the ultimate example. There are many "piano lessons" along that journey.
Sure, you can take off at 2am and leave a screaming 2 month old child in a room and never come back, because you have been trying for hours to stop it from crying and it is just too fucking hard - just like you can walk out of your piano lesson and never go back.
Why would I want my phone to auto reboot without my intervention? Never mind that it’ll never make three days on a single charge even if I don’t touch it.
It is not clear to me at all why the ‘benefits’ presented outweigh the negatives (which is _my_ device doing anything without me instructing it to). Even if you can turn it off, this is apparently enabled by default.
Law enforcement keeping hold of my phone for 3 days is simply not a realistic problem for me. Coming back to an annoyingly locked phone after forgetting it for a weekend very much is. The chances of law enforcement wanting anything with it are low enough that dealing with an extra unlock is more likely to be an impactful issue, even considering the potential impact that law enforcement or others stealing it could have.
> Coming back to an annoyingly locked phone after forgetting it for a weekend very much is.
It is?
I mean, my iPhone asks me for my passcode every 7 days anyways. And that's the only thing that happens on reboot anyways.
Also, you forget your phone for a weekend? How do you do anything during that weekend, like keep in touch with loved ones, get driving directions, pull up a boarding pass, check for delays, look up restaurants?
Easy, do what we did before mobile phones—civilization existed for thousands years and worked quite well without them (Rome built an empire sans mobile phones, so did the English). We even ran and coordinated the largest and most organized event in human history—WWII—without them!
Some of us have not yet succumbed to phone addiction (I often go for quite some days without using a phone and still have a normal life).
Hey, if you want to go back to life in Ancient Rome, with the disease and lack of medicine, the slavery, the dictatorship... I'm not going to stop you.
When you say civilization worked quite well for thousands of years, as an argument against mobile phones, I'm not sure you've quite thought your argument through... unless it's always been your dream to be a Russian serf, or an Egyptian slave?
There's no point further arguing about this matter with someone who hasn't lived through both pre and post mobile phone eras.
I'll just add this, I was amongst the first to ever own a cellular mobile phone. I owned several Motorola 'bricks' (DynaTAC) if you're old enough to know what that is, and before that I owned a mobile car phone in pre-cellular times, the nature of that tech was such that very few phone numbers were available—simply it was damed expensive and one had to be very keen to own one.
What I'm taking about is a lot more complex than your understanding (or that which you wish to admit to).
> Also, you forget your phone for a weekend? How do you do anything during that weekend, like keep in touch with loved ones, get driving directions, pull up a boarding pass, check for delays, look up restaurants?
Lmao I regularly go several days without calling family and months between any of those others.
Claude is almost comically good outside of copilot. When using through copilot it’s like working with a lobotomized idiot (that complains it generated public code about half the time).
It used to be good, or at least quite decent in GH Copilot, but it all turned into poop (the completions, the models, everything) ever since they announced the pricing changes.
Considering that M$ obviously trains over GitHub data, I'm a bit pissed, honestly, even if I get GH Copilot Pro for free.
If you get a hang of controlling costs, it's much cheaper. If you're exhausting the context window, I'm not surprised you're seeing high cost.
Be aware of the "cache".
Tell it to read specific files, never use /compact (that'll bust cache, if you need to, you're going back and forth too much or using too many files at once).
Never edit files manually during a session (that'll bust cache). THIS INCLUDES LINT.
Have a clear goal in mind and keep sessions to as few messages as possible.
Write / generate markdown files with needed documentation using claude.ai, and save those as files in the repo and tell it to read that file as part of a question.
I'm at about ~$0.5-0.75 for most "tasks" I give it. I'm not a super heavy user, but it definitely helps me (it's like having a super focused smart intern that makes dumb mistakes).
If i need to feed it a ton of docs etc. for some task, it'll be more in the few $, rather than < $1. But I really only do this to try some prototype with a library claude doesn't know about (or is outdated).
For hobby stuff, it adds up - totally.
For a company, massively worth it. Insanely cheap productivity boost (if developers are responsible / don't get lazy / don't misuse it).
Sure, it might cost a few dollars here and there. But what I've personally been getting from it, for that cost, is so far away from "expensive" it's laughable.
Not only does it do things I don't want to do, in a _super_ efficient manner. It does things I don't know how to do - contextually, within my own project, such that when it's done I _do_ know how to do it.
Like others have said - if you're exhausting the context window, the problem is you, not the tool.
Example, I have a project where I've been particularly lazy and there's a handful of models that are _huge_. I know better than to have Claude read those models into context - that would be stupid. Rather - I tell it specifically what I want to do within those models, give it specific method names and tell it not to read the whole file, rather search for and read the area around the method definition.
If you _do_ need it to work with very large files - they probably shouldn't be that large and you're likely better off refactoring those files (with Claude, of course) to abstract out where you can and reduce the line count. Or, if anything, literally just temporarily remove a bunch of code from the huge files that isn't relevant to the task so that when it reads it it doesn't have to pull all of that into context. (ie: Copy/paste the file into a backup location, delete a bunch of unrelated stuff in the working file, do your work with claude then 'merge' the changes to the backup file and copy it back)
If a few dollars here and there for getting tasks done is "too expensive" you're using it wrong. The amount of time I'm saving for those dollars is worth many times the cost and the number of times that I've gotten unsatisfactory results from that spending has been less than 5.
I see the same replies to these same complaints everywhere - people complaining about how it's too expensive or becomes useless with a full context. Those replies all state the same thing - if you're filling the context, you've already screwed it up. (And also, that's why it's so expensive)
I'll agree with sibling commenters - have claude build documentation within the project as you go. Try to keep tasks silo'd - get in, get the thing done, document it and get out. Start a new task. (This is dependent on context - if you have to load up the context to get the task done, you're incentivized to keep going rather than dump and reload with a new task/session, thus paying the context tax again - but you also are going to get less great results... so, lesson here... minimize context.)
100% of the time that I've gotten bad results/gone in circles/gotten hallucinations was when I loaded up the context or got lazy and didn't want to start new sessions after finishing a task and just kept moving into new tasks. If I even _see_ that little indicator on the bottom right about how much context is available before auto-compact I know I'm getting less-good functionality and I need to be careful about what I even trust it's saying.
It's not going to build your entire app in a single session/context window. Cut down your tasks into smaller pieces, be concise.
If this is truly your perspective, you've already lost the plot.
It's almost always the users fault when it comes to tools. If you're using it and it's not doing its 'job' well - it's more likely that you're using it wrong than it is that it's a bad tool. Almost universally.
Right tool for the job, etc etc. Also important that you're using it right, for the right job.
Claude Code isn't meant to refactor entire projects. If you're trying to load up 100k token "whole projects" into it - you're using it wrong. Just a fact. That's not what this tool is designed to do. Sure.. maybe it "works" or gets close enough to make people think that is what it's designed for, but it's not.
Detailed, specific work... it excels, so wildly, that it's astonishing to me that these takes exist.
In saying all of that, there _are_ times I dump huge amounts of context into it (Claude, projects, not Claude Code - cause that's not what it's designed for) and I don't have "conversations" with it in that manner. I load it up with a bunch of context, ask my question/give it a task and that first response is all you need. If it doesn't solve your concern, it should shine enough light that you now know how you want to address it in a more granular fashion.
The unpredictable non-deterministic black box with an unknown training set, weights and biases is behaving contrary to how it's advertised? The fault lies with the user, surely.
A junior developer is skilled too, but still requires a senior’s guidance to keep them focused and on track. Just because a tool has built in intelligence doesn’t mean it can read your intentions from nothing if you fail to communicate to it well.
How can one develop this skill via trial and error if the cost is unknowably high? Before reasoning, it was less important when tokens are cheap, but mixing models, some models being expensive to use, and reasoning blowing up the cost, having to pay even five bucks to make a mistake sure makes the cost seem higher than the value.
A little predictability here would go a long way in growing the use of these capabilities, and so one should wonder why cost predictability doesn’t seem to be important to the vendors - maybe the value isn’t there, or is only there for the select few that can intuit how to use the tech effectively.
Thanks for sharing. Are you able to control the context when using Claude Code, or are you using other tools that give you greater control over what context to provide? I haven't used Claude Code enough to understand how smart it is at deciding what context to load itself and if you can/need to explicitly manage it yourself.
I like the scribe analogy. And, just like a scribe, my primary complaint with claude code isn't the cost or the context - but the speed. It's just so slow :D
True. Matches my experience. It takes much effort to get really proficient with ai. It's like learning to ride a wild horse. Your senior dev skills will sure come handy in this ride but don't expect it to work like some google query
reply