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

411–420 of 732 posts

Re: Claude Code is being dumbed down?

#411

Post by noodletheworld »

bcherny wrote: post #402
steinnes wrote: post #400

Earlier quoted context omitted.

I can’t count how many times I benefitted from seeing the files Claude was reading, to understand how I could interrupt and give it a little more context… saving thousands of tokens and sparing the context window. I must be in the minority of users who preferred seeing the actual files. I love claude code, but some of the recent updates seem like they’re making it harder for me to see what’s happening.. I agree with…

I think folks might be crossing wires a bit. To make it so you can see full file paths, we repurposed verbose mode to enable the old explicit file output, while hiding more details behind ctrl+o. In effect, we've evolved verbose mode to be multi-state, so that it lets you toggle back to the old behavior while giving you a way to see even more verbose output, while still defaulting everyone else to the condensed view.…

How do you respond to the comment that; given the log trace:

“Did something 2 times”

That may as well not be shown at all in default mode?

What useful information is imparted by “Read 4 files”?

You have two issues here:

1) making verbose mode better. Sure.

2) logging useless information in default.

If you're not imparting any useful information, claude may as well just show a spinner.

Re: Claude Code is being dumbed down?

#412

Post by npunt »

alphazard wrote: post #288
bunderbunder wrote: post #249

Earlier quoted context omitted.

I have worked with some really really good product managers. But not lately. Lately it’s been people who have very little relevant domain expertise, zero interest in putting in the time to develop said expertise beyond just cataloguing and regurgitating feedback from the customers they like most on a personal level, and seem to mostly have only been selected for the position because they are really good at office pol…

There are individuals who have good taste for products in certain domains. Their own preferences are an accurate approximation for those of the users. Those people might add value when they are given control of the product. That good taste doesn't translate between domains very often. Good taste for developer tools doesn't mean good taste for a video game inventory screen. And that's the crux of the problem. There is…

Taste is pretty transferable, I think what you're talking about is intuition. The foundations of intuition are deeply understanding problems and the ability to navigate towards solutions related to those problems. Both of these are relatively domain-dependent. People can have intuition for how to do things but lack the taste to make those solutions feel right.

Taste on the other hand is about creating an overall feeling from a product. It's holistic and about coherence, where intuition is more bottom-up problem solving. Tasteful decisions are those that use restraint, that strike a particular tone, that say 'no' when others might say 'yes'. It's a lot more magical, and a lot rarer.

Both taste and intuition are ultimately about judgment, which is why they're often confused for one another. The difference is they approach problems from the opposite side; taste from above, intuition from below.

I agree with your assessment otherwise, PM can be a real smoke screen especially across domain and company stage.

Re: Claude Code is being dumbed down?

#413

Post by extr »

bcherny wrote: post #402
steinnes wrote: post #400

Earlier quoted context omitted.

I can’t count how many times I benefitted from seeing the files Claude was reading, to understand how I could interrupt and give it a little more context… saving thousands of tokens and sparing the context window. I must be in the minority of users who preferred seeing the actual files. I love claude code, but some of the recent updates seem like they’re making it harder for me to see what’s happening.. I agree with…

I think folks might be crossing wires a bit. To make it so you can see full file paths, we repurposed verbose mode to enable the old explicit file output, while hiding more details behind ctrl+o. In effect, we've evolved verbose mode to be multi-state, so that it lets you toggle back to the old behavior while giving you a way to see even more verbose output, while still defaulting everyone else to the condensed view.…

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 the last 4 messages, with the rest hidden behind ctrl+e.

It's not an easy UI problem to solve in all cases since behavior in CC can be so flexible, compaction, forking, etc. But it would be great if it was simply consistent (ctrl+o shows last N where N is like, 50, or 100), with ctrl+e revealing the rest.

Re: Claude Code is being dumbed down?

#414

Post by jy14898 »

eptcyka wrote: post #36

Can we not like, just apply a patch? Or will anthropic be mad if I run their client with my own patch? Nix makes it easy to package up esotheric patches reliably and reproducibly, claude lowers the cost of creating such patches, the only roadblocks Inforesee are legal.

https://github.com/aleks-apostle/claude-code-patches/pull/9 is what I found, not tested yet

Re: Claude Code is being dumbed down?

#415

Post by akdev1l »

massysett wrote: post #404
akdev1l wrote: post #354

Earlier quoted context omitted.

Not safe, before even knowing if a site has the content you want you can be redirected to malware through ad networks not even joking

On an up to date Safari on Mac, not a realistic concern, and if it were, I’d use security software, not an ad blocker.

0 days exist and they are exploited in the wild sometimes

An ad-blocker /is/ security software. You don’t have to take it from me, you can read from the Cybersecurity and Infrastructure Security Agency

> AT-A-GLANCE RECOMMENDATIONS

> Standardize and Secure Web Browsers

> Deploy Advertisement Blocking Software

> Isolate Web Browsers from Operating Systems

> Implement Protective Domain Name System Technologies

Literally their second recommendation on this pamphlet about securing web browsers: https://www.cisa.gov/sites/default/files/publications/Capaci...

Moreover you don’t even need a 0-day to fall for phishing. All you need is to be a little tired or somehow not paying attention (inb4 “it will never happen to ME, I am too smart for that”)

Re: Claude Code is being dumbed down?

#417

Post by ares623 »

kshri24 wrote: post #389

Hilarious! Anthropic can just vibe code the boolean flag in.

I think they already do? Which is commendable tbh. But I keep my popcorn ready and warm for the day when their vibe coding can't keep up with the codebase. Of course they will try their best to hide that fact for as long as possible.

Re: Claude Code is being dumbed down?

#418

Post by Denzel »

minimaxir wrote: post #123
theappsecguy wrote: post #98

Earlier quoted context omitted.

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

Believe me, I wish it was just parroting. The real annoying thing about Opus 4.5 is that it's impossible to publicly say "Opus 4.5 is an order of magnitude better than coding LLMs released just months before it" without sounding like a AI hype booster clickbaiting, but it's the counterintuitive truth, to my personal frustration. I have been trying to break this damn model since its November release by giving it compl…

Weird, I broke Opus 4.5 pretty easily by giving some code, a build system, and integration tests that demonstrate the bug.

CC confidently iterated until it discovered the issue. CC confidently communicated exactly what the bug was, a detailed step-by-step deep dive into all the sections of the code that contributed to it. CC confidently suggested a fix that it then implemented. CC declared victory after 10 minutes!

The bug was still there.

I’m willing to admit I might be “holding it wrong”. I’ve had some successes and failures.

It’s all very impressive, but I still have yet to see how people are consistently getting CC to work for hours on end to produce good work. That still feels far fetched to me.

Re: Claude Code is being dumbed down?

#419

Post by bcherny »

extr wrote: post #413
bcherny wrote: post #402

Earlier quoted context omitted.

I think folks might be crossing wires a bit. To make it so you can see full file paths, we repurposed verbose mode to enable the old explicit file output, while hiding more details behind ctrl+o. In effect, we've evolved verbose mode to be multi-state, so that it lets you toggle back to the old behavior while giving you a way to see even more verbose output, while still defaulting everyone else to the condensed view.…

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 -- fix incoming.

Re: Claude Code is being dumbed down?

#420

Post by Aeolun »

bcherny wrote: post #386

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 resulted in an experience that most users preferred

I just find that very hard to believe. Does anyone actually do anything with the output now? Or are they just crossing their fingers and hoping for the best?

Post reply on HN