> In a monorepo, just loading the project consumes ~20k tokens
This explains a lot. I don't work on a monorepo, and what I would consider a mid-size service is 7M tokens. I can't but ask: do all people who are so enthusiastic about AI only work on trivial projects?
charlesabarnes 14 minutes ago [-]
What scares me about Claude Code (and ai developer tools in general) is that a small model update could change how I interact with the tool entirely. There's no freezing the communication style that I need to use for good results.
Workaccount2 8 minutes ago [-]
I suspect that this is already a big reason why we get so many conflicting signals on "the best coding model". People tune into the style of the model they use the most, and hit snags and friction when they take another model for a spin.
Most iOS users report that Android is a disaster of an operating system, with layers and layers of user frustration. In reality, they actually are just totally in tune with how iOS does stuff. I can only imagine we have something similar going on here.
SatvikBeri 4 minutes ago [-]
For what it's worth, I've been using a fairly minimal setup (24 lines of CLAUDE.md, no MCPs, skills, or custom slash commands) since 3.7 and I've only noticed Claude Code getting significantly better on each model release.
fluidcruft 18 minutes ago [-]
I sort of agree with this about cognitive load. I'm somewhat new (started dipping my toes around July) but use Claude code heavily now. I did spend a lot of time playing with configuring it at first and creating agents etc. But I have a weird setup where I have three computers that I work on and at one point I realized vanilla Claude Code had adopted the things I was doing as defaults (and improved on them). So I have sort of declared a configuration bankruptcy and just use the recommended things. The only things I still do are things that help both Claude and I keep track of things (md files describing decisions and context of files).
[I still haven't figured out MCP or how/why to use them or why to bother. You run servers. I guess. It's too complex for my smol brain to understand]
buster 7 minutes ago [-]
I've not used Claude Claude yet, but why would it be bad if it gains features that people use?
Did people ever complain about Photoshop to have too many features demanding some cognitive load? Excel? Practically every IDE out there?
There is a reason people use those tools instead of the plain text editor or paint. It's for power users and people will become power users of AI as well. Some will forever stick to chatgpt and some will use an ever increasing ecosystem of tools.
ch2026 38 seconds ago [-]
because devs will have no clue how their systems work, the only ones who do will be LLMs, gatekept behind an ever-increasing cost-per-usage.
skydhash 3 minutes ago [-]
> With Opus 4.5, Claude Code feels like having a god-level engineer beside you. Opinionated but friendly. Zero ego.
> Claude was halfway through refactoring a complex auth flow[...] Then I realized: I'd forgotten to mention that one of those files was also used by a cron job.
That is the kind of research you do before you go to refactoring.
> Claude Code freed them from "the anxiety of the first step in programming constantly."
Is there a first step in programming? If there is, that would be thinking because you ought to get a good solution in mind before even typing the first line of code.
...
The whole article feels like someone roleplaying as software developer. Not that there's a barrier or a license to be one, but just that whole piece seems like as accurate as hackers portrayal in movies.
phplovesong 15 minutes ago [-]
SlopDX.
ltbarcly3 5 minutes ago [-]
"With Opus 4.5, Claude Code feels like having a god-level engineer beside you."
Well, not to me or the people I respect. It's getting very good, but it's like having a recent college grad who obsessively reads documentation. Someone with low skill but very high knowledge, often knowledge they are mixing up or not quite getting right.
I think if Claude is already 'better' at coding than you, maybe think about going back to college to be a lawyer or something. For the rest of us, lets just hope that Claude hits some natural limit before it gets better than us too. If it doesn't hit some limit I think we have a year or two.
dawnerd 1 minutes ago [-]
Yet when I try it, it feels like a developer fresh out of a coding bootcamp with no real experience. There’s no real reasoning, problem solving is still brute forced. It still rewrites rather than modifies. The context is way too limiting and it gets lost in its own “thinking”
ThouYS 16 minutes ago [-]
what on earth is a DX?
ycuser2 15 minutes ago [-]
Developer Experience (as in UX - User Experience)
15 minutes ago [-]
royal_ts 15 minutes ago [-]
Developer Experience
lnbharath 1 hours ago [-]
Author here. I wrote this because everyone is talking about Claude Code right now and it's all over my timeline. Claude Code has this effect where you KNOW it's good but can't quite say WHY.
So I spent the weekend digging into the DX decisions that make Claude Code delightful.
MasterScrat 17 minutes ago [-]
How much AI did you use to write up this article? It tripped up my "fake AI-written article" detector a few times despite being interesting enough to read to the end
lnbharath 5 minutes ago [-]
used claude to polish the draft and tighten sentences. the thinking, analysis, and examples are all mine and based on personal experiences. spent the weekend reflecting on my past experiences with claude code and actually digging into why claude code feels the way it does. curious to know what tripped your detector.
geophph 4 minutes ago [-]
“Here’s the thing”
“The best part?”
erichocean 26 seconds ago [-]
Do you have any sources you've found that document Claude Code's UI in detail? I'm really curious about what they've built, as a UI designer.
GiorgioG 9 minutes ago [-]
If only LLMs didn’t just make shit up regularly.
erichocean 2 minutes ago [-]
If a coding agent was released that never made anything up, how much would that change things for you?
Rendered at 16:55:00 GMT+0000 (Coordinated Universal Time) with Vercel.
This explains a lot. I don't work on a monorepo, and what I would consider a mid-size service is 7M tokens. I can't but ask: do all people who are so enthusiastic about AI only work on trivial projects?
Most iOS users report that Android is a disaster of an operating system, with layers and layers of user frustration. In reality, they actually are just totally in tune with how iOS does stuff. I can only imagine we have something similar going on here.
[I still haven't figured out MCP or how/why to use them or why to bother. You run servers. I guess. It's too complex for my smol brain to understand]
> Claude was halfway through refactoring a complex auth flow[...] Then I realized: I'd forgotten to mention that one of those files was also used by a cron job.
That is the kind of research you do before you go to refactoring.
> Claude Code freed them from "the anxiety of the first step in programming constantly."
Is there a first step in programming? If there is, that would be thinking because you ought to get a good solution in mind before even typing the first line of code.
...
The whole article feels like someone roleplaying as software developer. Not that there's a barrier or a license to be one, but just that whole piece seems like as accurate as hackers portrayal in movies.
Well, not to me or the people I respect. It's getting very good, but it's like having a recent college grad who obsessively reads documentation. Someone with low skill but very high knowledge, often knowledge they are mixing up or not quite getting right.
I think if Claude is already 'better' at coding than you, maybe think about going back to college to be a lawyer or something. For the rest of us, lets just hope that Claude hits some natural limit before it gets better than us too. If it doesn't hit some limit I think we have a year or two.
So I spent the weekend digging into the DX decisions that make Claude Code delightful.