461–470 of 489 posts
Earlier quoted context omitted.
I suspect subscription limits are quite a bit higher than the equivalent tokens their dollar cost could purchase. I similarly feel like I can get a lot done with a $20/mo Claude Pro subscriptions, but also can easily spend $10-20/day at API pricing with similar usage.
I don't understand why people are using the API pricing instead of the Pro/Max subscriptions? What am I missing?
Earlier quoted context omitted.
Maxed out the 200 dollar per month plan then incurred the overage. This was over the span of 1 month or so.
thanks, yeah i thought how'd it have to be time constrained, maxed out the monthly allotment. that makes sense. also using the latest model will burn those tokens. I've been so psychologically frugal with my token usage that's why i'm very curious about it all. it's a different paradigm, as an engineer, to go from "software should be free" to watching a meter tick at every turn. thanks for sharing.
The more nuanced question is what are the economics for tasks with ambiguous roi. I spent 100 dollars optimizing a build/ci system on Friday because it made me “feel” more productive. The result of about 24 hours of gpt5.5 in codex was a build time reduction of 75%.
Earlier quoted context omitted.
> % of AI suggestions accepted vs. edited is also a BS metric I disagree. It’s a valuable metric if you are building an agent / skill infra layer. Think of it like error rate on your API. Green metric does not mean your system is healthy, but if it’s red you have an issue you definitely need to fix. Your example scenario is detectable in the non-naive implementation anyway; the o11y layer (usually OTel these days) tr…
Not the one down-voting you btw. Disagreeing is fine by me. I would ask you tho: What incentive do AI vendors have to even try and detect this? It's in their interest to use the most naive interpretation, i.e. what my original comment mentioned, as it shows how "good" their models are, coz nobody ever changes much if anything ;) Never mind that they really can't unless they're going "creepy mode". If I use Claude/Cod…
I think I better understand your point now. I was mostly arguing for this as an internal metric inside the model user’s company, I agree it’s less useful coming directly from Anthropic’s measurements.
What I meant by “agent / skill infra layer” is if you’re a big company and trying to write skills that are widely shared, build common tooling for thousands of engineers to use agents within a big repo, etc.
RE “creepy”, I dunno, this case doesn’t bother me, but I can see why it might. It’s definitely being done though.
Earlier quoted context omitted.
I think quantifying tokens used is analogous to quantifying the amount of sawdust generated on a construction site. Churning out useful code quickly is not solved by using more tokens per unit time. Most non-technical leaders can grasp this one and are likely more interested in the strategic game theoretical dynamics that are being forced by way of implied token consumption expectations (competition between developer…
To understand the token count thing - spending tokens is necessary and not sufficient to demonstrate that you are adopting AI. Where we were 6mo ago is that a lot of big orgs realized they were behind, and needed some way of measuring if the tools were usable at all. No sawdust at all on your job site, and you can tell nobody is cutting wood. Now that tooling is more mature, you can measure things like % of diffs AI-…
It is oddly unprecendeted economic behavior.
Earlier quoted context omitted.
I'm a little the opposite, what's the point of using an IDE with AI? I genuinely don't get it? These days I just use Claude Code Desktop or Claude Code in powershell. Standalone, not inside and IDE. Honestly, I'm using Desktop more and more as it gets more features. The IDE is for me. No AI in it at all. If I want to get Claude to do something specific to a file I just @ the file.
Productivity. You generate the skeleton of the code with Codex/Claude Code/et. al. and refactor it manually. It's kind of unlikely that an AI agent will be able to one-shot every bit of code in the exact way you want, even with a fat AGENTS.md file. With a smart AI-native IDE like Zed, it will quickly be able to pick up what manual change you intent to do without you fully typing out anything, especially if they're r…
I have 2 monitors, Claude on one, IDE on the other.
Earlier quoted context omitted.
I'm a little the opposite, what's the point of using an IDE with AI? I genuinely don't get it? These days I just use Claude Code Desktop or Claude Code in powershell. Standalone, not inside and IDE. Honestly, I'm using Desktop more and more as it gets more features. The IDE is for me. No AI in it at all. If I want to get Claude to do something specific to a file I just @ the file.
the obvious answer is because it's easier , faster, and more efficient to flip a true to false right in front of you than it is to prompt an llm. if your response is "my prompts don't produce code that needs values flipped, ever." then I would wager you're only touching very simple things with an LLM. for me I don't care about the token cost and prompt writing so much as the fact that it's just faster to change 0 to…
Claude is in a terminal, I'm inspecting, reviewing, refactoring in my IDE.
Earlier quoted context omitted.
I'm a little the opposite, what's the point of using an IDE with AI? I genuinely don't get it? These days I just use Claude Code Desktop or Claude Code in powershell. Standalone, not inside and IDE. Honestly, I'm using Desktop more and more as it gets more features. The IDE is for me. No AI in it at all. If I want to get Claude to do something specific to a file I just @ the file.
That’s like asking why anyone would use IDE autoformatting, linting, or build tools rather than constantly swapping to a terminal to run their command line versions. As in, why use tool integration in an integrated development environment? Because that’s the entire point. Classic IDE refactoring and code generation tools are limited to explicitly programmed operations, but a well-integrated LLM can do much more and s…
Both of us working on the same code side-by-side. Window-by-window in my case.
And my IDE isn't infested with AI popups and extra menu items and lost real estate or anything trying to guess what I'm typing.
Earlier quoted context omitted.
> frequency bias Gaslighting again, Anthropic shill. What does frequency bias have to do with the objective fact that hundreds of people reported their own experiences with LLMs being degraded over a short period of time? The very same tasks that the very same LLMs could do, they no longer can? You seem to ignore this FACT, this DATA, and instead have to gaslight and divert into "frequency bias" nonsense. I do unders…
> What does frequency bias have to do with the objective fact that hundreds of people reported This isn't hard to understand "Model is nerfed" claim hits social media Someone else sees it, frequency bias makes them think their model is also nerfed, and they amplify the claim Now it spreads, like a virus, even if the model never changed Social dynamics like this are well understood psychologically > If the LLM used to…
Did you really just claim that people are so gullible that it was social media or whatever that made them believe their LLM could no longer achieve the tasks it yesterday could, and not the actual FACT of LLM not being able to do it that they, you know, verified before complaining online? I guess if you gaslight everything like that, then indeed no matter what the facts are, you will never be convinced in anything.
You see, because of outlandish claims and reasoning (or rather lack of) like that, everyone sees that you are an Anthropic shill.
Earlier quoted context omitted.
#1 -> part of scaling is you can't review every single line of code. LLMs don't really scale if you're still the bottlneck, or they only scale as much as you reviewing every line of code - that's not that much scaling... So I try to only review certain parts, like making sure they aren't changing tests to allow architecturally broken code to slip through (because they regularly try, even when given explicit instructi…
> LLMs don't really scale if you're still the bottlneck This only works if there's no consequences if your code breaks. In the eyes of other humans you're responsible for what you commit. No amount of "scaling" will change that.
You're only responsible for what you merge to master, not everything you commit to a feature branch no one is looking at...
If you have the testing and the infrastructure in place such that you can't ship broken code, then you just need to make sure your invariants are upheld - not that every single line is beautiful and perfect.
Further, I am working on a set of metrics that seems pretty good at identifying sloppy architecture. There's decent prior art at many different components of what "sloppy" architecture actually is, and ways to visualize it.
If you can rely on the consensus of several different models, plus your own judgement with the design and the testing in place to verify its implemented correct...
Then, 1) you don't need to code. 2) you only need to review 1/10th or less of the code written. That scales. Reading every line of code line by line doesn't really scale. LLMs aren't very fast at implementation outside of green-field projects. So you can often times implement something faster than they will if you did it by hand. Reviewing can take just as much time as implementing...