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

501–510 of 732 posts

Re: Claude Code is being dumbed down?

#501

Post by arexxbifs »

DANmode wrote: post #472
johndough wrote: post #403

Earlier quoted context omitted.

DeepSeek had a theoretical profit margin of 545 % [1] with much inferior GPUs at 1/60th the API price. Anthropic's Opus 4.6 is a bit bigger, but they'd have to be insanely incompetent to not make a profit on inference. [1] https://github.com/deepseek-ai/open-infra-index/blob/main/20...

> they'd have to be insanely incompetent to not make a profit on inference. Are you aware of how many years Amazon didn’t turn a profit? Not agreeing with the tactic - just…are you aware of it?

Amazon was founded in 1994, went public in 1997 and became profitable in 2001. So Anthropic is two years behind with the IPO but who knows, maybe they'll be profitable by 2028? OpenAI is even more behind schedule.

Re: Claude Code is being dumbed down?

#502

Post by somewhereoutth »

alphazard wrote: post #216
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…

Apple was built on a product manager shouting at engineers until they got it right.

Re: Claude Code is being dumbed down?

#503

Post by bostonvaulter2 »

bcherny wrote: post #443
btown wrote: post #436

Earlier quoted context omitted.

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…

> 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 be clear: we re-purposed verbose mode to do exactly what…

> To be clear: we re-purposed verbose mode to do exactly what you are asking for. We kept the name "verbose mode", but the behavior is what you want, without the other verbose output.

Verbose mode feels far too verbose to handle that. It’s also very hard to “keep your place” when toggling into verbose mode to see a specific output.

Re: Claude Code is being dumbed down?

#504

Post by bostonvaulter2 »

dinp wrote: post #486
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.…

I thought I was the only person going crazy by the new default behavior not showing the file names! Please don't expect users to understand your product details and config options in such detail, it was working well before, let it remain. Or at least show some message like "to view file names, do xyz" in the ui for a few days after such a change. While we're here, another thing that's annoying: the token counter. Whi…

> Another thing: is it possible to turn off the words like finagling and similar (I can't remember the spelling of any of them) ?

Big +1 on that. I find the names needlessly distracting. I want to just always say a single thing like “thinking”

Re: Claude Code is being dumbed down?

#506

Post by nazgul17 »

bcherny wrote: post #496
consumer451 wrote: post #469

Earlier quoted context omitted.

This is an interesting and complex ui decision to make. Might it have been better to retire and/or rename the feature, if the underlying action was very different? I work on silly basic stuff compared to Claude Code, but I find that I confuse fewer users if I rename a button instead of just changing the underlying effect. This causes me to have to create new docs, and hopefully triggers affected users to find those d…

Yeah, in hindsight, we probably should have renamed it.

It's not too late.

Re: Claude Code is being dumbed down?

#507

Post by 2001zhaozhao »

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…

At some point we need to start preferring GUIs instead of terminals as the AI starts giving us more and more information. Features like hover-over tooltips and toggle switches designed for mouse operation might really start to matter.

Maybe "AI IDEs" will gain ground in the future, e.g. vibe-kanban

Re: Claude Code is being dumbed down?

#508

Post by JohnMakin »

misnome wrote: post #81
thousand_nights wrote: post #34

Earlier quoted context omitted.

i've never had to use control + o before but with the latest changes, i give Opus a simple task that should take a few seconds and it's like "used 15k tokens" and "thinking" for three minutes with absolutely zero indication or visibility as to what it's actually doing and i have to ESC ESC it to stop and ask what the FUCK are you actually doing claude?

Yes, I’ve been evaluating since the start of the year and since 4.6 suddenly the most innocuous requests will sit there “thinking” for 5+ minutes and if I can get it to show me the thinking it’s just going round in circles. Or, it decided it needs to get API documentation out and spends tens of thousands of tokens fetching every file in a repo with separate tool use instead of reading the documentation. Profitable, i…

I guess I engineered around this before 4.6 - I did notice a regression in it wanting to search deeper than I wanted and had specified, but just restricted it with tooling I wrote that would enforce what I wanted. In that respect, I feel comfortable running 4.6 with the guardrails I already have, but did notice some squirrelyness I didnt anticipate in my utility scripts.

It is clever. its its best and worst feature.

Re: Claude Code is being dumbed down?

#509

Post by 1f60c »

cyanydeez wrote: post #498
1f60c wrote: post #482

Earlier quoted context omitted.

Thariq (who's on the Claude Code team) swears up and down that they do not do this. Honestly, man, this is just weird new tech. We're asking a probabilistic model to generate English and JSON and Bash at the same time in an inherently mutable environment and then Anthropic also release one or two updates most workdays that contain tweaks to the system prompt and new feature flags that are being flipped every which wa…

Yeah, I know it's new tech and the pipeline for the magic is a bunchof shims ontop of a non-deterministic models; but the MBAs are going to swoop in eventually and segmenting the users into tiers of price discrimnation is in the pike regardless of how earnest the current PMs are.

Hmm, honestly I'm not so sure. Many devs seem extremely price-sensitive and the switching cost is... zero.

If Anthropic do something you don't like, you just set a few environment variables and suddenly you're using the Claude Code harness with a local model, or one of thousands available through OpenRouter. And then there is also OpenCode. I haven't tried this, but I'm not worried.

^ https://github.com/ruvnet/claude-flow/wiki/Using-Claude-Code...

Re: Claude Code is being dumbed down?

#510

Post by jwpapi »

bcherny wrote: post #444
Wowfunhappy wrote: post #429

Earlier quoted context omitted.

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…

That's a cool idea!

Honestly Tmux, vim, kitty, almost every terminal, shell, script is configurable. It’s what we’re used to. I wouldn’t know why you wouldn’t start allowing more config options.
Post reply on HN