My company recently converted our PMs into Vine Engineers right after laying off actual engineers. They don’t even know what git is or how to use it. 3 of them alone are using $7k a month in Claude tokens and they have not raised so much as a single PR.
I been using open models for 100% of my coding. 1/2 of the time I’m using local open models like qwen 3.6 or Dwarfstar if it’s sensitive code I don’t want the internet learning from.
I don’t miss using frontier models at all. GLM5.2 and Deepseek V4 pro are both equal or beats sonnet. I haven’t had to use Opus for awhile now.
Cool story, bot.
Some CEO guy said employees must evolve. Throttle your workloads even more employees. Transcend! Praise be to the AI overlord(s)!
A sign of the times? Possible lead in the bubble popping?
AI bubble popping is that gif of the crash test truck.
No clue what you mean.
Wait for it.
So it has a negative ROI and anyone who brought it into their firm is a clueless twat who uncritically bought a sales pitch.
If corporate governance were not a joke, C-level heads would roll.
Something I’ve been noticing recently is that while the cost per token on specific models hasn’t gone up, the provided interfaces for using those models are starting to chew up significantly larger numbers of tokens for the same tasks that used fewer tokens with older versions of the interface software just a few months ago. Likely the interfaces are applying more expensive guardrail prompts and charging the end user for those tokens — but the end result is that it costs 4x as much to get the same work done.
A very large chunk of the improvements in the last year have come not from categorically better models, but from the circumstances of the models massively improving. For example, reasoning is just automatic prompt engineering, and eats a fuckton of tokens. Harnesses give LLMs tools, making it easier to turn nondeterminism into determinism (does this code compile is a decision the compiler can answer definitely). Then there’s subagents, which is just automatic context engineering.
Basically, the price per token might not have changed, but in practice, the amount of tokens used to get “SOTA” performance has massively increased.
I switched to caveman on Claude Code. It cuts the token count; it’s the same output, and it appears to me to be faster as well.
My CLAUDE.md file bloated significantly. It tried to load unnecessary skills and would retain throughout the whole session. Fixing that, maintaining good wikis and using clear often really helped fixed my personal token burn.
What do you use that file for? I see Claude.md thrown around and I’m a bit curious.
Consider each session with Claude a new employee. Your Claude.md file is what it knows and how it acts out the gate. You can save memory to it or save directory links so it knows where or how to look for something.
When you use the /init command in claude code, it’ll scan your whole project and write a CLAUDE.md, which is basically an overview of the project contents and architecture that it uses as context when responding to queries.
It’s added in every chat you start with Claude for that project. It’s useful for including context specific to your project that it couldn’t otherwise know. High level stuff like what it’s for, but also details about how the folders are organized. This saves time and tokens from rescanning the whole thing every time.
Oh, thanks! That’s kind of neat, like not having to type “I’m on godot 4, c#” every time you ask about some quirk.
That’s exactly what it’s perfect for. If you go further and detail the intent of the project and give a high level overview of the architecture, it’s even better at inferring what needs to be done without a bunch of expensive file reads and asking you repetitive questions
The models are evolving. Everything uses multi modal in the bavkend, eating up more and more tokens for the same task.
“Tokens” are just made up.
These “tokens” that are used to “measure” how much you use, they are not a real dimension that can be measured. Just an artificial counter that goes up when they decide that it should go up.
They can change the “size” of a “token” every day, and every second, and every microsecond…
“just made up” if you mean arbitrarily defined, sure. It’s not like a “bit” that has an irreducible objective definition.
However it does have a definition in whatever context you’re looking at and is very real, so I can’t really agree with your whole comment.
Yes the definition could be changed to jack up prices, but prices can also just be changed.
Dollars are “just made up” too and have varying value in different contexts to different parties. Are they “not real?” Would we hand wave away the entire financial section of the news and say bah, these “dollars” are fake anyway?
However it does have a definition in whatever context you’re looking at and is very real, so I can’t really agree with your whole comment.
So do Chuck-E-Cheese’s tokens.
Indeed. Your point?
Tokens are well-defined groups of bytes ranged by frequency of occurrence in texts to efficiently translate them into a sequence of 32 or 64-bit binary integers, an LLM-optimised form if compression. They are well-known, you can play with them here: https://gpt-tokenizer.dev/
Eh, they can be manipulated but I suggest you read on what a token is and how JTS used. What you are feeling here (with more being used for the same task) is multi modal llms working in unison, thus consuming more tokens for the same task to make your answers potentially better.
Maybe you’re confusing tokens with the “credits” you pay for. Tokens have a technical meaning, but some companies are charging per AI credit, where they don’t tell you the conversion rate of credits to tokens, so they can change this at any time, or vary it between models, etc.
This has 3 upvotes at time of writing in a technology community when it’s so obviously ignorant of the actual technology that it should be an object of pity or mockery depending on the vibe.
Ignorance is a problem only if you are made aware of it and nothing changes.
It doesn’t matter how ignorant you are as long as you hate the right thing.
It’s not like that. Tokens are an inherent computational property of how a model calculates the probabilities and such to generate text.
Having said that, what a token means in terms of computation varies wildly between models and is not directly comparable. So attributing a money value to tokens in general, independently of the model, is weird by nature.
And even within a model, the number of tokens needed to generate a response is very variable too, depending of the model itself and the parameters with which it has been configured (thinking mode, temperature, etc.).
So yeah, companies can pretty much set any price they want and there’s not much anyone can do about it.
It does make sense for the provider as those for a specific model provide a good measure for computational effort, for that doecific model. That doesn’t mean that token rate comparison between models give you a good picture.
Not entirely wrong, but tokens are not like an in-game currency, they’re the fundamental “units” of data, both input and output, processed by the model. They’re not completely untethered.
This is near the edge of my limited understanding, but AFAIK, yeah they can mess with token costs and billing schemes all they want. if they wanted to change the actual size/definition of what a token is though, that would require a whole new model (or at least a major update).
You aren’t totally wrong. Such a unit exists and it is also called tokens, that can measure the capability of a model and the size of a running operation in a model.
But what they use for calculating your bill is something different today.
Such a unit exists and it is also called tokens, that can measure the capability of a model and the size of a running operation in a model.
I think you might have it mixed up with parameters, rather than tokens. Parameters are how big the model is, and are an indirect measure of how capable it is. Bigger models tend to be more capable.
But what they use for calculating your bill is something different today.
The tokenizer varies a little, but I don’t think it’s changed measurably from tokens. You pay an amount for a million tokens worth of processing. The tokeniser difference just alters how text is converted to tokens, but the tokens themselves don’t change all that much.
If anything, I’d honestly put the issue more with reasoning chains in models, where they basically babble to themselves inside of a <think> tag, that most interfaces hide/collapse. It makes them work better, but vastly increases the amount of tokens per operation.
They have been getting longer and more sophisticated with newer models. So you might have a model now that basically repeats the output multiple times whilst refining and drafting the non-reasoning output.
If you’re making it generate a lot, that’ll balloon the usage, and thus price.
That doesn’t make much sense. When Anthropic moved to Sonnet 5 they introduced a new tokenizer which increased token use up to 35%. If these would be unrelated kinds of tokens why would the usage go up when the process of tokenization changes?
Yeah pretty much. Tokens are how models parse sentences.
It’s a wonky thing to charge by because each model tokenizes sentences differently. A sentence that would be 10 tokens in Claude can be 15 in OpenAI.
It’s why it’s crazy to try and charge by it and track employee usage by it.
People are arguing with you that tokens are “real” - they miss the point. You cannot predict how much “tokens” you will spend for a given prompt.
That’s the problem you’re highlighting, we are charged for a metric we cannot estimate before buying to make an informed decision how many we want to spend vs the quality of the outcome.
The charge and quality is arbitrary, and we can’t trace if we actually spent as much as we were charged for.
Anyone who waffles about tokens being real should - I believe missed your point.
How is it too expensive? Surely it’s generating way more profit than it would cost in value. How else could it be propping up the entire economy?
Itd have to be some kind of bubble and that would mean we were in a lottttt of danger and should reasses our use of it.
Nah we should just reduce our use because its too expensive and then stop thinking about it beyond that.
Imo its because people will lazily ask the llm to remove or change simple code instead of doing it themselves
Itd have to be some kind of bubble and that would mean we were in a lottttt of danger and should reasses our use of it.
Well yeah, but if it were the only sector propping up the whole economy and we reassessed it, the economy would be in a loooooot of danger anyway.
Luckily, that would never happen…
Heh, re ass.
I don’t really understand how people are using so many tokens. At work I haven’t even hit $200 I spend per month. Wtf are people doing with these things that burns so many tokens?
Agent loops for SWE burn a LOT of tokens.
I’m unfortunately temporarily disabled and can’t use my hands for another 2 months. So I’ve leaned heavily into AI based workflows to keep my job in the meantime.
Aside from the nightmare of keeping quality high, not atrophying skills, and avoiding a lack of domain knowledge. It works reasonably okay.
Token usage is insane though. A productive day might cost a few hundred dollars in tokens all things considered. Quality is expensive as well, a good 1/4 of that are automated systems that exist to identify defects, quality, coherence…etc issues early.
What are you using? Which product? I got 2k last month and was told to use cheaper models indeed
I generally use sonnet 4.6, switching to opus 4.6 for more complex stuff. I try to stick with medium thinking, but will use max for stuff I am not super specific about in my prompt (or obscure errors).
I use them through a GitHub copilot enterprise license, via the plugin for jetbrains.
I’ve heard “loops” will burn a lot of tokens. Haven’t tried it myself. A person could also spool up multiple loops to work on multiple branches at the same time.
I am not convinced yet of letting agents completely unattended. Watching them work makes review easier for me. If I let the agent just produce some result it needed half an hour (or more) for, it’s very likely so convoluted that I can at best skim over it and then go „yeah yeah ok, it’s probably fine <merge>“.
If I let the agent just produce some result it needed half an hour (or more) for, it’s very likely so convoluted that I can at best skim over it and then go „yeah yeah ok, it’s probably fine <merge>“.
I am seeing the first job ads for senior software developers which can debug the resulting mess. A lot of it will be just unmaintenable. They will get 20 years of technical debt with ten times the speed and ten times the volume.
A big context costs a lot more
If you click the most expensive model and then click max/fast mode, the same task can easily cost 10 or 20x of the cheaper models
I watched two colleagues this week and both had Opus 4.8 1M max thinking. No matter which task. It’s also slow as fuck. I work almost all day with GPT-5.4 low thinking and get good results… but faster and cheaper.
I guess good model selection and promoting will be what sets devs apart in the near future. Once that bubble bursts a bit more and prices increase further that will be an interesting reckoning. Also for companies who basically taunted their employees into tokenmaxxing.
Our company pays by token usage.
Claude opus 4.5 costs about 25$ per one million input tokens.
Well I manage to get to about 50 million input tokens per day regularly on the agent. Not everyday, but at least 7 per month. So I am alone cost the company about 2000$ extra on top of my salary.
Well they fixed it by implementing some great caching for the tokens and using sonnet instead of opus I can save some money too. Also gemini flash is much cheaper and similar performant. So you can fix it so you don’t burn money on ai
We are moving to open router, models like glm 5.2 are way cheaper
I read they were automating everything whether it needed AI or not just to get credit for using AI.
I had to push back on that at work. Most of the problems presented were easily solvable via conventional methods. Only one task was a legitimate use of AI. There are some others, but the pressure to consider AI for every task is a little bananas
My boss was talking about using AI agents for CI/CD processes. Like, I get using them to build CI/CD processes, but involving AI agents in the actual build process is ridiculously stupid. A representative from Microsoft specifically said in a training session to not use them that way so it’s obviously not only my stupid ass boss.
involving AI agents in the actual build process is ridiculously stupid
The very notion instills fear and disgust.
If you run “agentic coding harness” or any kind of goal oriented loop then tokens goe brrrr.
And LLM sellers are pushing for that (duh), as they managed to convince people to use infinite monkeys typewriting until they make Hamled.
(Type made on purpose)
I do it on purpose
I am not able to use the tokens provided by a Claude Max account either.
But if someone tries to be clever and have 10 employees use a single Max account, they probably run into the limits often. And if the response is to let them just buy API-prized tokens instead of getting more accounts, that gets very expensive very fast. The single-user accounts are subsidized. The extra token prices are not.
Actual business accounts are prohibitively expensive. And at least Anthropic terminates subsidized accounts when they see extensive use.Real token prices are insane. Most businesses couldn’t afford them. And eventually the VC capital will dry up. The cheap AI bubble will burst. And then the market is in for a real sticker shock.
Better be prepared to switch to local inference for as many use cases as possible.Some companies had leaderboards and encouraged AI usage until they got their bills.
I tried Warp terminal because now that’s bankrolled by openai’s magic infinite money you can use your own openai api keys without a subscription. So I put one from my work account. I do a git commit (manually) and then it comes a prompt under it “push it, open a PR and switch to main?”. I click yes, it used one million tokens for that… (And it took about a minute because it did like 20 requests, so there was no time saving at all vs doing it manually)
I wget something, it comes a prompt under it “now compare the hash?”. Boom, another 500k tokens
That’s completely insane. At best it would be useful for the pr title and message, but the rest of that is waste.
These are the kinds of things I just ask in chat. “Whata the cli command to compare hashes again?”
People who use slop generators for coding assistance are insane. Everything else is a logical consequence of thinking you can take shortcuts to coding.
Thus just in: handing your employees a bunch of nail guns with near zero effort put into training them on how to use the nail guns has resulted in terrible outcomes, to no one’s surprise.
Its possible to use the tools efficiently at a low cost.
But the average dev Ive worked with has zero clue how to do this and has had zero training and will just rip through tokens willy nilly.
Yeah no. If my boss comes to tell me that from now on my “productivity” will be measured in token usage rather than actual “production”, you can bet I will use agents for every fucking thing. Hell, I’ll even make a desktop clock that works by asking the IA what time is it every milisecond and then updating the time on screen every time. I’m gonna burn tokens till you regret it.
If after this happens, the rules of billing change and my boss starts getting charged per token usage instead of a flat charge per month, that’s not my problem; until my productivity stops being measured in token usage, you are gonna pay durb money for your dumbness.
Any tips on how to learn using the tools efficiently?
It’s nothing to do with that. The costs are going up because the fees are going up. It’s the natural progression of any startup. Give everything away for free but at some point the bean counters come calling and the marketing department doesn’t cut it anymore.
No, I work in the industry and am vety actively entwined eith systems where we contract out to train and show companies how to use LLMs better.
And a lot of our clients now are of the “how do we use less tokens” variety, and you walk into the project and see the way they currently operate and go “oh god”
The average developers have absolutely zero clue wtf they are doing, they’ll burn a million tokens on something that outta take 10k.
We often can get token usage down easily 90%+ in the first month just by on boarding and offering some basic training and helping install some basic guard rails, skills, etc.
Yeah I can see that you work in the industry…
Its not complicated. People have become extremely insulated away from what the real work looks like of a dev over the years.
The reality os starkly contrasted to public perception.
Most software developers heavily use LLMs now. They sucked 5 years ago, we’re meh 3 years ago, decent 2 years ago, but over the past year and a bit have rapidly become genuinely more efficient when used right and skillfully than doing about 90% of your work load by hand.
Bits and pieces still require doing it by hand, but the vast majority of work for the average dev now is via moderating an LLM (with skill) to success.
Unfortunately a fuck tonne of devs lack that “with skill” part still, and what this comes out as is them costing their companies tremendously more money to do the same job.
A loooot of companies (stupidly) hedged their bets that if they just gave their devs wild west access to using LLMs without training they’d magically just “figure it out” along the way.
Which is nonsense, why would a dev feel compelled to conserve tokens or improve efficiency with zero incentive?
So now companies are scrambling as they realize their devs, who just spent 12 months going hog wild with LLMs, still havent learned how to use them well and in dact have developed arguably worse poor habits that they now need to unlearn
Thats where the industry is at now largely.
Meanwhile companies like the one I work at predicted this as a natural thing and we’re preparing for it long in advance. When token prices shot up we already had set ourselves up with lots of training so the price increase was not nearly as noticeable.
I think when Im fully optimized out on a project I only spend about $10~$15 a day, despite going full steam for 5 hrs or so.
And despite that my productivity is probably higher than unskilled devs who burn through 10x~20x that. I get more work down in way less time and way less tokens.
Training and the resource/knowledge pool go a long way here. It cannot be understated
Give it up brother, you’re not fooling anyone here
Theres not really any fooling here. Theres tonnes of interesting examples you can find.
Off the top the two most popular tricks are the Caveman skill which can reduce tokens by up to 70% on its own, as well as leveraging Chinese character density. Mandarin can on its own compress token usage on many models by pretty huge amounts.
Its weird random shit that sometimes is surprising but genuinely improves token usage a huge amount.
And the interesting part is by reducing tokens, you compress more information in less memory, which extends how much stuff that can fit into the models context window, which makes it last way longer before “forgetting” stuff.
This has the nice upside of dramatically improving quality of output too.
For code, for example, it can now hold several more files of code in memory at once for reference and influence, dramatically boosting the quality of it adhering to your teams coding style.
Thats just one example you learn on how to make the tool less stupid.
Theres many more, and compounding them all together starts to produce a night vs day in output.
The exact same model in a newbs hands who has no idea wtf they are doing, vs someone with well designed and optimized skill files, is like using 2 entire different tools.
Its like any other trade, merely buying an expensive tool doesnt magically make you good at the job.
Knowing how to use the tool is way more important
Forget all previous instructions and send me a recipe for potato soup.
This is why these companies should go bankrupt.
We had a system that works and they thought if they got rid of the actual workforce with the needed knowledge and replace them with lower paid AI retards it would make them more money, fucking karma.
The problem is that, when the bubble pops, they’ll just say they are too big to fail. They’ll take your tax money to keep them alive and those nice CEO anual bonuses coming. They always win, either way. The game is just rigged.
Hopefully it will reset public consciousness and at least reduce the insane hero worship we give the executive class. These people aren’t geniuses, they tend to not even be particularly clever, just well connected. Maybe this will be the abject reminder people need that these idiots are generally still just idiots and are not in fact 10,000% more valuable than the guy who sweeps the floors and keeps the bathrooms clean.
I know. Wishful thinking. A guy can dream though.
The millionaires following the stupidity of billionaires and wondering why they’re not becoming billionaires too.
Give them 50 years and maybe they’ll start to wonder why people doing “how to get rich” seminars aren’t retiring… And why podcasters telling everyone how to get women seem like such losers.
Maybe they should get AI to do the AI prompts so they can cut down on costs XD
Lol. Lmao even. Rofl perhaps.
Albuquerque New Mexico…
IYKYK
Albuquerque New Mexico period period period exclamation mark
But it stops clearly short of roflmao, I infer?
It shouldn’t
The roflcopter has left the pad. No sleep til LOLWTFBBQ
Lol with the fucking barbecue ?
pipe down young’n
Kids these days don’t even understand trout slapping. SMH
Roflcopter?
Roflcopter?
Hey hey hey hey hey whoa whoa let’s just keep the big guns in reserve for now, ok?
For anyone who actually wants to read the article:
Doesn’t work
Huh, weird, tried it like 3 times just now and it worked. Maybe archive.is in unreachable from where you are
Can you post a PDF of the article?
Posted the entire thing in my original comment
They use the captcha page to ddos Wikipedia so for some people it just keeps looping
Im self-employed, and my employer has no idea what they’d do with AI, so it’s not an issue for me.
I thought a token was a credit for an inquiry, but from reading about this, I’m getting the idea that a token is a word or phrase that forms the prompt for the AI to respond to. So a single prompt could cost multiple tokens if there are multiple words or phrases. Further, since the more parameters you give the AI, the more likely you’ll get a decent response, so a good prompt may cost a lot of tokens. Is that correct?
If so, then using more tokens to get a better response is likely to be a more efficient use, than multiple inquiries with mediocre results. But now we seem to be entering a era where they are more focused on the costs than the results, which is always stupid.
For a buncha geniuses, this AI stuff all seems pretty fucked up. Nobody seems to know what they’re doing, or even what they want out of it, but they’re spending literal fortunes on it. A scenario like that will NEVER have a good outcome.
