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

431–440 of 732 posts

Re: Claude Code is being dumbed down?

#431

Post by trb »

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.…

I've commented on this ticket before: https://github.com/anthropics/claude-code/issues/8477#issuec...

The thinking mode is super-useful to me as I _often_ saw the model "think" differently from the response. Stuff like "I can see that I need to look for x, y, z to full understand the problem" and then proceeds to just not do that.

This is helpful as I can interrupt the process and guide it to actually do this. With the thinking-output hidden, I have lost this avenue for intervention.

I also want to see what files it reads, but not necessarily the output - I know most of the files that'll be relevant, I just want to see it's not totally off base.

Tl;dr: I would _love_ to have verbose mode be split into two modes: Just thinking and Thinking+Full agent/file output.

---

I'm happy to work in verbose mode. I get many people are probably fine with the standard minimal mode. But at least in my code base, on my projects, I still need to perform a decent amount of handholding through guidance, the model is not working for me the way you describe it working for you.

All I need is a few tools to help me intervene earlier to make claude-code work _much_ better for me. Right now I feel I'm fighting the system frequently.

Re: Claude Code is being dumbed down?

#432

Post by tristor »

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.

Not hype. Opus 4.5 is actually useful to one-shot things from detailed prompts for documentation creation, it's actually functional for generating code in a meaningful way. Unfortunately it's been nerfed, and Opus 4.6 is clearly worse from my few days of working with it since release.

Re: Claude Code is being dumbed down?

#433

Post by ctoth »

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'm a screen reader user and CTO of an accessibility company. This change doesn't reduce noise for me. It removes functionality.

Sighted users lost convenience. I lost the ability to trust the tool. There is no "glancing" at terminal output with a screen reader. There is no "progressive disclosure." The text is either spoken to me or it doesn't exist.

When you collapse file paths into "Read 3 files," I have no way to know what the agent is doing with my codebase without switching to verbose mode, which then dumps subagent transcripts, thinking traces, and full file contents into my audio stream. A sighted user can visually skip past that. I listen to every line sequentially.

You've created a situation where my options are "no information" or "all information." The middle ground that existed before, inline file paths and search patterns, was the accessible one.

This is not a power user preference. This is a basic accessibility regression. The fix is what everyone in this thread has been asking for: a BASIC BLOODY config flag to show file paths and search patterns inline. Not verbose mode surgery. A boolean.

Please just add the option.

And yes, I rewrote this with Claude to tone my anger and frustration down about 15 clicks from how I actually feel.

Re: Claude Code is being dumbed down?

#434

Post by latchkey »

bcherny wrote: post #427
rmujica wrote: post #407

Earlier quoted context omitted.

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..

i thought about it being ai generated, but i don't care. it was easy to read and contained the right information. good enough for me. plus, who knows... maybe you were english as a second lang and used ai to clean up your writing. i'd prefer that.

Re: Claude Code is being dumbed down?

#436

Post by btown »

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.…

I'll add a counterpoint that in many situations (especially monorepos for complex businesses), it's easy for any LLM to go down rabbit holes. Files containing the word "payment" or "onboarding" might be for entirely different DDD domains than the one relevant to the problem. As a CTO touching all sorts of surfaces, I see this problem at least once a day, entirely driven by trying to move too fast with my prompts.

And so the very first thing that the LLM does when planning, namely choosing which files to read, are a key point for manual intervention to ensure that the correct domain or business concept is being analyzed.

Speaking personally: Once I know that Claude is looking in the right place, I'm on to the next task - often an entirely different Claude session. But those critical first few seconds, to verify that it's looking in the right place, are entirely different from any other kind of verbosity.

I don't want verbose mode. I want Claude to tell me what it's reading in the first 3 seconds, so I can switch gears without fear it's going to the wrong part of the codebase. By saying that my use case requires verbose mode, you're saying that I need to see massive levels of babysitting-level output (even if less massive than before) to be able to do this.

(To lean into the babysitting analogy, I want Claude to be the babysitter, but I want to make sure the babysitter knows where I left the note before I head out the door.)

Re: Claude Code is being dumbed down?

#437

Post by Aeolun »

tmaly wrote: post #362
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.

I thought the source code for the actual CLI was closed source. How are you patching it?

Claude code can reverse engineer it to a degree. Doing it for more than a single version is a PITA though. Easier to build you own client over their SDK.

Re: Claude Code is being dumbed down?

#438

Post by amai »

noosphr wrote: post #376
amai wrote: post #364

Earlier quoted context omitted.

OpenAI’s president is a Trump mega-donor https://news.ycombinator.com/item?id=46771231

>Of all tyrannies, a tyranny sincerely exercised for the good of its victims may be the most oppressive. It would be better to live under robber barons than under omnipotent moral busybodies. The robber baron's cruelty may sometimes sleep, his cupidity may at some point be satiated; but those who torment us for our own good will torment us without end for they do so with the approval of their own conscience. They may…

The article is about Greg Brockman, president of OpenAI.

Re: Claude Code is being dumbed down?

#439

Post by Aeolun »

exitb wrote: post #206
kakugawa wrote: post #183

Earlier quoted context omitted.

How much longer is Anthropic going to allow OpenCode to use Pro/Max subscriptions? Yes, it's technically possible, but it's against Anthropic's ToS. [1] 1: https://blog.devgenius.io/you-might-be-breaking-claudes-tos-...

Consider switching to an OpenAI subscription, which allows OpenCode use.

Yeah. OpenAI allows any client, and only one single fixed system prompt. All their control is on the backend, which is worse than Claude.

Re: Claude Code is being dumbed down?

#440

Post by holoduke »

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…

To be honest I think there should be an option to completely hide all code that Claude generates and uses. Summaries, strategies, plans, logs, decisions and questions is all I need. I am convinced that in a few years nobody cares about the programming language itself.
Post reply on HN