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

661–670 of 732 posts

Re: Claude Code is being dumbed down?

#661

Post by Grimblewald »

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 Claude user who has been burned lately by how opaque the system has become. My workflows aren't long and my projects are small in terms of file count, but the work is highly specialized. It is "out of domain" enough that I'm getting "what is the seahorse emoji" style responses for genuine requests that any human in my field could easily follow. I've been testing Claude on small side projects to check its reliability. I work at the cutting edge of multiple academic domains, so even the moderate utiltity I have seen in this is exciting for me, but right now Claude cannot be trusted to get things right without constant oversight and frequent correction, often for just a single step. For people like me, this is make or break. If I cannot follow the reasoning, read the intent, or catch logic disconnects early, the session just burns through my token quota. I'm stuck rejecting all changes after waiting 5 minutes for it to think, only to have to wait 5 hours to try again. Without being able to see the "why" behind the code, it isn't useful. It makes typing "claude" into my terminal an exercise in masochism rather than the productivity boost it's supposed to be. I get that I might not be the core target demographic, but it's good PR for Anthropic if Claude is credited in the AI statements of major scientific publications. As it stands, trajectory in develeopment means I cannot in good conscience recommend Claude Code for scientific domains.

Re: Claude Code is being dumbed down?

#662

Post by bluesnowmonkey »

Along the same lines: I want the context window percentage visible at all times, not just when it drops below 10%. By that point it's too late to do anything useful. I can't even get it to finish up and dump its state to a file before the window is full. If I could see the percentage the whole time, I could pace my work and wrap things up cleanly instead of slamming into the wall.

Re: Claude Code is being dumbed down?

#663

Post by jatora »

Grimblewald wrote: post #661
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 Claude user who has been burned lately by how opaque the system has become. My workflows aren't long and my projects are small in terms of file count, but the work is highly specialized. It is "out of domain" enough that I'm getting "what is the seahorse emoji" style responses for genuine requests that any human in my field could easily follow. I've been testing Claude on small side projects to check its reliab…

What academic domains are you on the cutting edge of? Genuinely curious what specifically is beyond claude's capabilites

Re: Claude Code is being dumbed down?

#664

Post by johndough »

elzbardico wrote: post #636
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...

Deepseek lies about costs systematically. This is just another fantasy.

What do you base your accusations on? Is there a specific number from the link above that you claim is a lie?

And how are 7 other providers able to offer DeepSeek API access at roughly the same price as DeepSeek?

https://openrouter.ai/deepseek/deepseek-v3.2

Re: Claude Code is being dumbed down?

#665

Post by adastra22 »

JV00 wrote: post #616
adastra22 wrote: post #592

Earlier quoted context omitted.

We don’t want verbose mode. We don’t want the whole file contents. We are not asking for that. What is not clear here? All we want is the file paths. That is all. Verbose mode pulls in a lot of other information that might very well be needed in other contexts. People who want that info should use verbose mode. All we want is the regular non-verbose mode, with paths. I fail to see how it is confusing to users, even n…

Verbose mode does exactly what you want as of v2.1.39, you are confusing it with the full transcript which is a different feature (ctrl+o). You enable verbose mode in /config and it gives you files read and search patterns and token count, not whole file contents.

Please don’t change what these modes do! I have scripts that call into the agent SDK with verbose mode output for logging purposes. Now I guess I need to recreate the old verbose mode for that application? Why?

Re: Claude Code is being dumbed down?

#666

Post by vrighter »

mrandish wrote: post #377
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…

> you need an internal crusade to fight these impulses. Take the high road in the short-term... Anthropic is the market leader for advanced AI coding with no serious competitor currently very close and they are preparing to IPO this year. This year is a transition year. The period where every decision would default toward delighting users and increasing perceived value is ending. By next year they'll be fully on the…

"Preparing to ipo"

Prepare for everyone's subscriptions to shoot through the roof!

Re: Claude Code is being dumbed down?

#667

Post by johndough »

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?

Did Amazon really not turn a profit, or apply a bunch of tricks to make it appear like they didn't in order to avoid taxes? Given their history, I'd assume the later: https://en.wikipedia.org/wiki/Amazon_tax_avoidance

Anyway, this has nothing to do with whether inference is profitable.

Re: Claude Code is being dumbed down?

#668

Post by Grimblewald »

jatora wrote: post #663
Grimblewald wrote: post #661

Earlier quoted context omitted.

I'm a Claude user who has been burned lately by how opaque the system has become. My workflows aren't long and my projects are small in terms of file count, but the work is highly specialized. It is "out of domain" enough that I'm getting "what is the seahorse emoji" style responses for genuine requests that any human in my field could easily follow. I've been testing Claude on small side projects to check its reliab…

What academic domains are you on the cutting edge of? Genuinely curious what specifically is beyond claude's capabilites

Most recent problems were related to topology, but it can take the wrong direction on many things. This is not an LLM fault; it's a training data issue. If historically a given direction of inquiry is favored, you can't fault an LLM for being biased toward it. However, if small volume and recent results indicate that path is a dead end, you don't want to be stuck in fruitless loops that prevent you from exploring other avenues.

The problem is if you're interdisciplinary, translating something from one field to one typically considered quite distant, you may not always be aware of historic context that is about to fuck you. Not without deeper insight into what the LLM is choosing to do or read and your ability to infer how expected the behavior you're about to see is.

Re: Claude Code is being dumbed down?

#670

Post by NateEag »

insanedeisgn wrote: post #613
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…

[flagged]

Please don't post LLM output and pretend it's your writing.

I never thought I'd long for the days when people posted "$LLM says" comments, but at least those were honest.

Post reply on HN