Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

What Claude Code chooses

amplifying.ai

Post reply on HN
Print view View original

171–180 of 266 posts

Re: What Claude Code chooses

#171

Post by torginus »

empath75 wrote: post #98
cryptonector wrote: post #76

Earlier quoted context omitted.

We used to reuse code a lot. But then we got problems like diamond dependency hell. Why did we reuse code a lot? To save on labor. Now we don't have to. So we might roll-your-own more things. But then we'll have a tremendous amount of code duplication, effectively, and bigger tech debt issues, minus the diamond dependency hell issue. It might be better this way; time will tell.

Speaking of rolling your own things, i had claude knock out a trello clone for me in 30 minutes because i was irritated at atlassian. I am already using it for keeping track of personal stuff. I’m not going to make a product out of it or even put it on github. It’s just for me. There are gonna be a lot of single team/single user projects. It is so fast to build working prototypes that it’s not even worth thinking if…

I'm sure after you've had Claude build it, you learned a ton of how to build such a thing (I certainly did for my projects).

Basically, the data model is dead simple, you just spin up a SQLite db, create a React frontend, grabbing a good drag and drop library that implements these cards, write some simple but decent looking CSS, some React and backend boilerplate to wire the thing together - and boom - you're done.

This sounds simple when I write like this, but the complexity comes from knowing what library to use, figuring out its API, and assembling the whole thing together - which Claude is great at, but once you see the whole thing put together, you come to understand these things as well, and become more skilled at building stuff like this.

Re: What Claude Code chooses

#172

Post by OJFord »

jaunt7632 wrote: post #160
karel-3d wrote: post #159

Earlier quoted context omitted.

any information about it? what did they sell? I don't even see a sales link on tailwind page

[dead]

That's an incomplete story though, 'revenue has plummeted due to LLMs', 'revenue is from people sponsoring the project', so... what, people that formerly liked and sponsored Tailwind stopped, figuring they can just ask AI now?

Bit surprised that would have happened in significant volume (I'd have thought the LLM using non-sponsors would have far more overlap with the prior non-sponsors) but maybe.

Re: What Claude Code chooses

#173

Post by jascha_eng »

jascha_eng wrote: post #166
jaunt7632 wrote: post #124

[dead]

@dang this accounts comments smell like LLM slop. They are mostly on topic and its more claude than chatgpt but it's slop nontheless. is telling didn't win... It won ... Look at their other comments they are also fishy I know you guys don't want us to call it out because of negativity. But there needs to be awareness in the community, this is the top comment somehow right now. It feels like it happens every other thr…

Note I might be wrong on this one but it's just extremely annoying that I even have to consider if I am being manipulated by an AI while reading HN comments.

If I want to read AI stuff I go to Clawdbook or OpenAIs Sora app.

Re: What Claude Code chooses

#174

Post by loktarogar »

OJFord wrote: post #172
jaunt7632 wrote: post #160

Earlier quoted context omitted.

[dead]

That's an incomplete story though, 'revenue has plummeted due to LLMs', 'revenue is from people sponsoring the project', so... what, people that formerly liked and sponsored Tailwind stopped , figuring they can just ask AI now? Bit surprised that would have happened in significant volume (I'd have thought the LLM using non-sponsors would have far more overlap with the prior non-sponsors) but maybe.

Their offering was paid-for bundles of components and templates using tailwind, which they primarily drove traffic to via their documentation, which wasn't getting visited as much anymore because people just used AI.

Re: What Claude Code chooses

#175

Post by codingconstable »

deaux wrote: post #154

Supreme irony: this website itself is a better exercise in showing what Claude Code uses than the data provided. Everything current Claude Code i.e. Opus 4.6 chooses by default for web is exactly what this linked blog uses. Jetbrains Mono is as strong of a tell for web as "Not just A, but B" for text. >99% of webpages created in the last month with Jetbrains Mono will be Opus. Another tell is the overuse of this font…

Yeah its those bars for categories for me, they look EXACTLY like something I vibed (with no particular style prompt) into existence yesterday

Re: What Claude Code chooses

#176

Post by PeterStuer »

piokoch wrote: post #164
jaunt7632 wrote: post #124

[dead]

"Tailwind didn't win because it's the best CSS solution. It won because it has the most tutorials per capita in the training set." Obviously. People keep forgetting that "Artificial Intelligence" does not think and is not intelligent. It just statistically predict next token in a sequence. It is all statistics. So, Django 6 has new task framework, but LLM does not care, as Celery has better stats. Side note: it is no…

"does not think and is not intelligent. It just statistically predict next token in a sequence. It is all statistics"

Technically correct, but pretty useless as a working model. Like sayin humans are not intelligent. It's just biochemical and bioelectric reactions. It's all physics.

How would you, from a Searlian perspective argue against "humans are just statistical next token predictors"?

Re: What Claude Code chooses

#179

Post by inandoutflux »

OJFord wrote: post #172
jaunt7632 wrote: post #160

Earlier quoted context omitted.

[dead]

That's an incomplete story though, 'revenue has plummeted due to LLMs', 'revenue is from people sponsoring the project', so... what, people that formerly liked and sponsored Tailwind stopped , figuring they can just ask AI now? Bit surprised that would have happened in significant volume (I'd have thought the LLM using non-sponsors would have far more overlap with the prior non-sponsors) but maybe.

You forget turnover. Sponsorship isn't a subscription with much value after you built your product. You have a number of people coming in and out on top of those staying put, and those former were probably the most important metric.

AI spewing answers out of the magic box (or even just one-shotting with zero oversight) means developers do not go to the actual website for documentation, do not share as many issues as much and do not talk about the experience of working with tailwind as much - AI performance discourse takes that attention. This means less in-flow, which means the line of stability will be lower even in a vacuum where people have no particular reason to increase the out-flow.

And yet, this isn't a vacuum. I am not arguing it's just that alone. I absolutely believe that people simply stopped valuing code altogether. Why pay for ready solutions when the beepity bopity boop handles custom implementation for you without you even having to ask too much? It's what the OP article here is saying, AI's love custom solutions.

Re: What Claude Code chooses

#180

Post by lelanthran »

empath75 wrote: post #98
cryptonector wrote: post #76

Earlier quoted context omitted.

We used to reuse code a lot. But then we got problems like diamond dependency hell. Why did we reuse code a lot? To save on labor. Now we don't have to. So we might roll-your-own more things. But then we'll have a tremendous amount of code duplication, effectively, and bigger tech debt issues, minus the diamond dependency hell issue. It might be better this way; time will tell.

Speaking of rolling your own things, i had claude knock out a trello clone for me in 30 minutes because i was irritated at atlassian. I am already using it for keeping track of personal stuff. I’m not going to make a product out of it or even put it on github. It’s just for me. There are gonna be a lot of single team/single user projects. It is so fast to build working prototypes that it’s not even worth thinking if…

> Speaking of rolling your own things, i had claude knock out a trello clone for me in 30 minutes because i was irritated at atlassian.

I knocked out a webapp to manage tickets, states, ETA, etc for me and me alone in about 30m, pre-AI.

Note: I have a pre-built very-low-code framework for doing CRUD applications that lets me do ugly but functional webapps.

Post reply on HN