Live data from Hacker News

Claude Code is being dumbed down?

symmetrybreak.ing

601–610 of 732 posts

Re: Claude Code is being dumbed down?

#601

There are a lot of non developer claude code users these days. The hype about vibe coding lets everyone think they can now be an engineer. Problem is if anthropic caters to that crowd the devs that are using it to do somewhat serious engineering tasks and don't believe in the "run an army of parallel agents and pray" methodology are being alienated. Maybe Claude Code web or desktop could be targeted to these new vibe…

> The hype about vibe coding lets everyone think they can now be an engineer. Programmers are just jealous that they are no longer the only ones that get to play pretend. I don't know anything about you personally, but most "software engineers" are anything but.

I am curious to know why you believe that?

I've worked as a software engineer with different types of engineers (electrical, mechanical and automation).

Their testing is often more strict but that is a natural consequence of their products being significantly harder to fix in the field than a software product is.

Other than that, my experience is that our way of working on projects across disciplines is very similar.

Re: Claude Code is being dumbed down?

#602
post #447

Earlier quoted context omitted.

Try Codex instead. Much greener pastures overall

I do love my subagents and I wrote an entire Claude Code audio hook system for a11y but this would be still rather compelling if Codex weren't also somewhat of an a11y nightmare. It does some weird thing with ... maybe terminal repaints or something else that ends up rereading the same text over and over. Claude Code does this similarly but Codex ends up reading like ... all the weird symbols and other stuff? window…

Sorry for being off-topic, but isn't a11y a rather ironic term for accessibility? It uses a very uncommon abbreviation type -- numeronym, and doesn't mean anything to the reader unless they look it up (or already know what it means).

Re: Claude Code is being dumbed down?

#603

Hey, Boris from the Claude Code team here. I wanted to take a sec to explain the context for this change. One of the hard things about building a product on an LLM is that the model frequently changes underneath you. Since we introduced Claude Code almost a year ago, Claude has gotten more intelligent, it runs for longer periods of time, and it is able to more agentically use more tools. This is one of the magical th…

clause is perfect every time, no quibbles, the IT industry is simply has to adapt to the new shift. surely people who earn a living by writing code will find fault with it, but even with Claude, code will not write itself, its a simple shift from writing code to make code work better/integrate/tweak/refine/personalize/customize it, thank you Boris and team we are over the moon over

Re: Claude Code is being dumbed down?

#604

Earlier quoted context omitted.

If you are talking about agents I feel like opencode has gotten pretty good UI/UX If you are talking about a CLI editor, then micro has hit the nail on quality UX https://micro-editor.github.io/

The UX where it completely breaks copy paste conventions on Linux? Other than that I agree it's gotten pretty good but this one thing drives me mad each time I use it.

I think that you can actually change the keybindings to follow the copy paste conventions that you want in micro

But personally I really love these new copy paste conventions, its the ctrl q convention which troubled me in ghostty but what I did was "ctrl > " write quit enter

https://github.com/micro-editor/micro/blob/master/runtime/he...

Re: Claude Code is being dumbed down?

#605
The dumbing down of LLMs seems to be working in my favor so far as my platform provides guardrails for LLMs by abstracting away complexity.

They could potentially dumb it down further, but if they did that, it would hurt other use cases and competitors much more.

Re: Claude Code is being dumbed down?

#606

Hey, Boris from the Claude Code team here. I wanted to take a sec to explain the context for this change. One of the hard things about building a product on an LLM is that the model frequently changes underneath you. Since we introduced Claude Code almost a year ago, Claude has gotten more intelligent, it runs for longer periods of time, and it is able to more agentically use more tools. This is one of the magical th…

This kind of attitude, above all else, is why anthropic is winning imo. Thanks.

Ignoring user input?

Re: Claude Code is being dumbed down?

#607
post #600

Hey, Boris from the Claude Code team here. I wanted to take a sec to explain the context for this change. One of the hard things about building a product on an LLM is that the model frequently changes underneath you. Since we introduced Claude Code almost a year ago, Claude has gotten more intelligent, it runs for longer periods of time, and it is able to more agentically use more tools. This is one of the magical th…

I am not a programmer and detest the terminal environment, while I design complexity, i need simple interfaces, claude is now guiding all dev based on my initial design spec, makes beatuful notebooks that can be uploaded directly to colab or github, no UX at all, no usability issues, this is the lastet baby we made yesterday starborn.github.io/copp-notebook thank you Claude engineering team for something that is flyi…

> I am not a programmer and detest the terminal environment

As someone who finds formal language a natural and better interface for controlling a computer, can you explain how and why you actually hate it? I mean not stuff like lack of discoverability, because you use a shell that lacks completion and documentation, that have been common for decades, I get those downsides, but why do you detest it in principle?

Re: Claude Code is being dumbed down?

#608
post #413

Earlier quoted context omitted.

FWIW I mentioned this in the thread (I am the guy in the big GH issue who actually used verbose mode and gave specific likes/dislikes), but I find it frustrating that ctrl+o still seems to truncate at strange boundaries. I am looking at an open CC session right now with verbose mode enabled - works pretty well and I'm glad you're fixing the subagent thing. But when I hit ctrl+o, I only see more detailed output for th…

Yes totally. ctrl+o used to show all messages, but this is one of the tricky things about building in a terminal: because many terminals are quite slow, it is hard to render a large amount of output at once without causing tearing/stutter. That said, we recently rewrote our renderer to make it much more efficient, so we can bump up the default a bit. Let me see what it feels like to show the last 10-20 messages -- fi…

Do you have any examples of slow terminals, and what kind of maximum characters per second they have?

Re: Claude Code is being dumbed down?

#609
One good solution should be mentioned here - run Claude under strace/ltrace/LD_PRELOAD/etc.

The fact that LLM miss to read files is crucial for solving tasks. It does not matter that LLM later say "Yeah, I've fully read the specification and here is your code" if you check the log and it says: "Reading SPEC.md lines 1-400" .

Overall, the complete log of interaction with the system should always be available, otherwise it is effectively a malware. That's not an exaggeration: consider that at any point of time any side part can spit out a prompt injection. Consider the use case: previously in xz-utils it was needed to sabotage the landlock kernel level sandbox, AND to exist in the memory of sshd, AND to be able to hijacking the RSA_public_decrypt. Now the only thing is needed - printf.

Re: Claude Code is being dumbed down?

#610
post #75

I really dislike this trend that unfortunately has become, well, a trend. And has followers. Namely, let's simplify to "reduce noise" and "not overwhelm users", because "the majority of users don't need…". This is spreading like a plague: browser address bars are being trimmed down to nothing. Good luck figuring out which protocol you're using, or soon which website you are talking to. The TLS/SSL padlock is gone, so…

The TLS thing at least kind of makes sense. 99.9% of sites that the typical user visits will have a correctly configured and trusted certificate and communicate over TLS, so the browsers only show an indicator when that’s not the case. I think it’s a sensible evolution given how the internet has changed.
Post reply on HN