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

421–430 of 732 posts

Re: Claude Code is being dumbed down?

#421

Post by bcherny »

noodletheworld wrote: post #411
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.…

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.

It's a balance -- we don't want to hide everything away, so you have an understanding of what the model is doing. I agree that with future models, as intelligence and trust increase, we may be able to hide more, but I don't think we're there yet.

Re: Claude Code is being dumbed down?

#422

Post by keybored »

mwigdahl wrote: post #282
keybored wrote: post #215

Earlier quoted context omitted.

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

Yes, as all of modern politics illustrates, once one has staked out a position on an issue it is far more important to stick to one's guns regardless of observations rather than update based on evidence.

I will change my mind on this in the next month.

Re: Claude Code is being dumbed down?

#423

Post by falcor84 »

teaearlgraycold wrote: post #396
falcor84 wrote: post #378

Earlier quoted context omitted.

I understand not exposing a full stack trace, but I don't see any excuse to not even expose a googleable error code. If me having an error code makes your product insecure, then you have a much bigger problem.

I show the stack trace on AGPL projects. Why hide what they can already see for themselves?

The reason I see is that it might expose the value of secret keys or other sensitive variables. But if you are certain it won't happen, then yes

Re: Claude Code is being dumbed down?

#424

Post by vikaveri »

bcherny wrote: post #399
cactusplant7374 wrote: post #390

Earlier quoted context omitted.

In what terminals is rendering slow? I really think GPU acceleration for terminals (as seen in Ghostty) is silly. It's a terminal. Edit: I can't post anymore today apparently because of dang. If you post a comment about a bad terminal at least tell us about the rendering issues.

VSCode (xterm.js) is one of the worst, but there's a large long tail of slow terminals out there.

Not really using VS Code terminal anymore, just Ubuntu terminal but the biggest problem I have is that at some point Claude just eats up all memory and session crashes. I know it's not really Claude's fault but damn it's annoying.

Re: Claude Code is being dumbed down?

#425

Post by bcherny »

Aeolun wrote: post #420
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?

Have you tried verbose mode? /config > verbose. It should do exactly what you are looking for now, without extraneous thinking/subagent/hook output. We hear the feedback!

Re: Claude Code is being dumbed down?

#426

Post by 4gotunameagain »

steinnes wrote: post #400
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…

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…

> saving thousands of tokens and sparing the context window

shhh don't say that, they will never fix it if means you use less tokens.

Re: Claude Code is being dumbed down?

#427

Post by bcherny »

rmujica wrote: post #407
latchkey wrote: post #394

Earlier quoted context omitted.

This is an insanely good response. History, backstory, we screwed up, what we're doing to fix it. Keep up the great work!

it reads like AI generated or at least AI assisted... those -- don't fool me!

fwiw, I wrote it 100% by hand. Maybe I talk to Claude too much..

Re: Claude Code is being dumbed down?

#428

Post by tern »

NewsaHackO wrote: post #270
tern wrote: post #135

Claude's brand is sliding dangerously close to "the Microsoft of AI." DEVELOPERS, DEVELOPERS, DEVELOPERS, DEVELOPERS I write mainly out of the hope that some Anthropic employees read this: you need an internal crusade to fight these impulses. Take the high road in the short-term and you may avoid being disrupted in the long-term. It's a culture issue. Probably your strongest tool is specifically educating people abou…

Huh? Why wouldn’t developers (who probably have stock options in Claude) try to prevent becoming 'the Microsoft of AI'? That's probably what they are actively trying to do.

This take is overly cynical. Every major corporation has people with influence who care and fight for good outcomes. They win some fights, they lose others. The only evidence you need is to notice the needlessly good decisions that were made in the past.

Some greatest hits:

- CoreAudio, Mac OS memory management, kernel in general, and many other decisions

- Google's internal dev tooling, Go, and Chrome (at least, in its day)

- C#, .NET, and Typescript (even Microsoft does good work)

One of the hallmarks of heroic engineering work is that everyone takes it for granted afterward. Open source browsers that work, audio that just works, successors to C/C++ with actual support and adoption, operating systems that respond gracefully under load, etc. ... none of these things were guaranteed, or directly aligned with short-term financial incentives. Now, we just assume they're a requirement.

Part of the "sensibility" I'm talking about is seeking to build things that are so boring and reliable that nobody notices them anymore.

Re: Claude Code is being dumbed down?

#429

Post by Wowfunhappy »

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.…

Honestly, I just want to be able to control precisely what I see via config.json. It will probably differ depending on the project. This is a developer tool, I don't see why you'd shy away from providing granular configuration (alongside reasonable defaults).

I actually miss being able to see all of the thinking, for example, because I could tell more quickly when the model was making a wrong assumption and intervene.

Re: Claude Code is being dumbed down?

#430

Post by exabrial »

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…

@boris

Can we please move the "Extended Thinking" icon back to the left side of claude desktop, near the research and web search icons? What used to be one click is now three.

Post reply on HN