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

Claude Code is being dumbed down?

symmetrybreak.ing

Post reply on HN
Print view View original

211–220 of 732 posts

Re: Claude Code is being dumbed down?

#211

Post by roughly »

vintagedave wrote: post #117

> That’s it. “Read 3 files.” Which files? Doesn’t matter. “Searched for 1 pattern.” What pattern? Who cares. Product manager here. Cynically, this is classic product management: simplify and remove useful information under the guise of 'improving the user experience' or perhaps minimalism if you're more overt about your influences. It's something that as an industry we should be over by now. It requires deep understa…

This also shifts over time - new users, especially people sophisticated in the field your tool is addressing, need to be convinced the product is doing what they believe it should be doing, and want to see more output from it. They may become comfortable with the product over time and move further up the trust/abstraction ladder, but at the beginning, verbose output is a trust-building mechanism.

Re: Claude Code is being dumbed down?

#212

Post by thisisit »

My last experience with Claude support was a fun merry go round.

I had used a Visa card to buy monthly Pro subscription. One day I ran out of credits so I go to buy extra credit. But my card is declined. I recheck my card limit and try again. Still declined.

To test the card I try extending the Pro subscription. It works. That's when I notice that my card has a security feature called "Secure by Visa". To complete transaction I need to submit OTP on a Visa page. I am redirected to this page while buying Pro subscription but not when trying to buy extra usage.

I open a ticket and mention all the details to Claude support. Even though I give them the full run down of the issue, they say "We have no way of knowing why your card was declined. You have to check with your bank".

Later I get hold of a Mastercard with similar OTP protection. It is called Mastercard Securecode. The OTP triggers on both subscription and extra usage page.

I share this finding with support as well. But the response is same - "We checked with our engineering team and we have no way of knowing why the other Visa card was declined. You have to check with your bank".

I just gave up trying to buy extra usage. So, I am not really surprised if they keep making the product worse.

Re: Claude Code is being dumbed down?

#213

Post by cactusplant7374 »

locusofself wrote: post #108

Working at Microsoft, I've just now hooked up to Claude Code (my department was not permitted to use it previously), through something called "Agent Maestro", a vscode extension which I guess pipes claude code API requets to our internally hosted Claude models, including Opus 4.6. I do wonder if there is going to be much of a difference between using Claude Code vs. Copilot CLI when using the same models.

Is this an indictment of OpenAI's models -- that Microsoft has access to through their investment?

Re: Claude Code is being dumbed down?

#214

Post by chickensong »

For a general tool that has such a broad user base, the output should be configurable. There's no way a single config, even with verbose mode, will satisfy everyone.

Set minimal defaults to keep output clean, but let users pick and choose items to output across several levels of verbosity, similar to tcpdump, Ansible, etc. (-v to -vvvvv).

I know businesses are obsessed with providing Apple-like "experiences", where the product is so refined there's just "the one way" to magically do things, but that's not going to work for a coding agent. It needs to be a unix-like experience, where the app can be customized to fit your bespoke workflow, and opening the man page does critical damage unless you're a wizard.

LLMs are already a magic box, which upsets many people. It'll be a shame if Anthropic alienates their core fan base of SWEs by making things more magical.

Re: Claude Code is being dumbed down?

#215

Post by keybored »

theappsecguy wrote: post #98
minimaxir wrote: post #52

Earlier quoted context omitted.

> If you hadn't realized, a LOT of companies switched to Claude. No idea why, and this is coming from someone who loves Claude Code. It is entirely due to Opus 4.5 being an inflection point codingwise over previous LLMs. Most of the buzz there has been organic word of mouth due to how strong it is. Opus 4.5 is expensive to put it mildly, which makes Claude Code more compelling. But even now, token providers like Open…

Everyone and I mean everyone keeps parroting this "inflection point" marketing hype, which is so damn tiring.

But I used to be a skeptic but now in the last month

Re: Claude Code is being dumbed down?

#216

Post by alphazard »

vintagedave wrote: post #117

> That’s it. “Read 3 files.” Which files? Doesn’t matter. “Searched for 1 pattern.” What pattern? Who cares. Product manager here. Cynically, this is classic product management: simplify and remove useful information under the guise of 'improving the user experience' or perhaps minimalism if you're more overt about your influences. It's something that as an industry we should be over by now. It requires deep understa…

Product management might be the worst meme in the industry. Hire people who have never used the product and don't think like or accurately represent our users, then let them allocate engineering resources and gate what ships. What could go wrong?

It should be a fad gone by at this point, but people never learn. Here's what to do instead: Find your most socially competent engineer, and have them talk to users a couple times a month. Just saved you thousands or millions in salaries, and you have a better chance of making things that your users actually want.

Re: Claude Code is being dumbed down?

#217

Post by rrrix1 »

TIPSIO wrote: post #198
SOLAR_FIELDS wrote: post #78

https://github.com/anthropics/claude-code/issues/8477 https://github.com/anthropics/claude-code/issues/15263 https://github.com/anthropics/claude-code/issues/9099 https://github.com/anthropics/claude-code/issues/8371 It's very clear that Anthropic doesn't really want to expose the secret sauce to end users. I have to patch Claude every release to bring this functionality back.

To be fair they have like 10,000 open issues / spam issues, it's probably insane out there for them to filter all of it haha

Humans don't look at these anymore, Claude itself does. They've even said so.

Re: Claude Code is being dumbed down?

#218

Post by NinjaTrance »

idopmstuff wrote: post #180
vintagedave wrote: post #117

> That’s it. “Read 3 files.” Which files? Doesn’t matter. “Searched for 1 pattern.” What pattern? Who cares. Product manager here. Cynically, this is classic product management: simplify and remove useful information under the guise of 'improving the user experience' or perhaps minimalism if you're more overt about your influences. It's something that as an industry we should be over by now. It requires deep understa…

Also product manager here. Not at all cynically, this is classic product management - simplify by removing information that is useful to some users but not others. We shouldn't be over it by now. It's good to think carefully about how you're using space in your UI and what you're presenting to the user. You're saying it's bad because they removed useful information, but then why isn't Anthropic's suggestion of using…

> It requires deep understanding of customer usage to know whether it's a mistake at all

Software developers like customizable tools.

That's why IDEs still have "vim keybindings" and many other options.

Your user is highly skilled - let him decide what he wants to see.

Re: Claude Code is being dumbed down?

#219

Post by ReptileMan »

taude wrote: post #48
ramon156 wrote: post #6

All my information about this is being based on feels, because debugging isn't really feasible. Verbose mode is a mess, and there's no alternative. It still does what I need so I'm okay with it, but I'm also on the $20 plan so it's not that big of a worry for me. I did sense that the big wave of companies is hitting Anthropic's wallet. If you hadn't realized, a LOT of companies switched to Claude. No idea why, and th…

I can't watch a YouTube video without seeing a Claude ad. Same for friends. Safe for non-programmer friends.

I can. I use brave

Re: Claude Code is being dumbed down?

#220

Post by chasd00 »

vjerancrnjak wrote: post #23
noupdates wrote: post #3

Quite frankly, most seasoned developers should be able to write their own Claude Code. You know your own algorithm for how you deal with lines of code, so it's just a matter of converting your own logic. Becoming dependent on Claude Code is a mistake (edit: I might be too heavy handed with this statement). If your coding agent isn't doing what you want, you need to be able to redesign it.

It's quite tricky as they optimize the agent loop, similar to codex. It's probably not enough to have answer-prompt -> tool call -> result critic -> apply or refine, there might be a specific thing they're doing when they fine tune the loop to the model, or they might even train the model to improve the existing loop. You would have to first look at their agent loop and then code it up from scratch.

I bet you could derive a lot by using a packet sniffer while using CC and just watch the calls go back and forth to the LLM API. In every api request you'll get the full prompt (system prompt aside) and they can't offload all the magic to the server side because tool calls have to be done locally. Also, LLMs can probably de-minimize the minimized Javascript in the CC client so you can inspect the source too.

edit: There's a tool, i haven't used it in forever, i think it was netsaint(?) that let you sniff https in clear text with some kind of proxy. The enabling requirement is sniffing traffic on localhost iirc which would be the case with CC

Post reply on HN