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

131–140 of 732 posts

Re: Claude Code is being dumbed down?

#131

Post by knodi »

co_king_3 wrote: post #83
palebluedot wrote: post #51

Earlier quoted context omitted.

> FWIW I think LLMs are a dead end for software development, and that the people who think otherwise are exceptionally gullible. By this do you mean there isn't much more room for future improvement, or that you feel it is not useful in its current form for software development? I think the latter is hard position to defend, speaking as a user of it. I am definitely more productive with it now, although I'm not sure…

> By this do you mean there isn't much more room for future improvement I don't expect that LLM technology will improve in a way that makes it significantly better . I think the training pool is poisoned, and I suspect that the large AI labs have been cooking the benchmark data for years to suspect that their models are improving more quickly than they are in reality. That being said, I'm sure some company will figur…

This is a bot.

Re: Claude Code is being dumbed down?

#132

Post by layer8 »

jtrn wrote: post #101

I find it hard to care about claims of degradation of quality, since this has been a firehouse of claims that don't map onto anything real and is extremely subjective. I myself made the claim in error. I think this is just as ripe for psychological analysis as anything else.

You seem to be referring to something else than the topic the article is about.

Re: Claude Code is being dumbed down?

#133

Post by resiros »

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.

Honestly, just use OpenCode. It works with Claude Code Max, and the TUI is 100x better. The only thing that sucks is Compaction.

Re: Claude Code is being dumbed down?

#134

Post by palebluedot »

co_king_3 wrote: post #83
palebluedot wrote: post #51

Earlier quoted context omitted.

> FWIW I think LLMs are a dead end for software development, and that the people who think otherwise are exceptionally gullible. By this do you mean there isn't much more room for future improvement, or that you feel it is not useful in its current form for software development? I think the latter is hard position to defend, speaking as a user of it. I am definitely more productive with it now, although I'm not sure…

> By this do you mean there isn't much more room for future improvement I don't expect that LLM technology will improve in a way that makes it significantly better . I think the training pool is poisoned, and I suspect that the large AI labs have been cooking the benchmark data for years to suspect that their models are improving more quickly than they are in reality. That being said, I'm sure some company will figur…

> IME using LLMs for software development corrodes my intuitive understanding of an enterprise codebase.

I feel you there, I definitely notice that. I find I can output high quality software with it (if I control the design and planning, and iterate), but I lack that intuitive feel I get about how it all works in practice. Especially noticeable when debugging; I have fewer "Oh! I bet I know what is going on!" eureka moments.

Re: Claude Code is being dumbed down?

#135

Post by tern »

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 about the history. Microsoft in the late 90s and early 00s was completely dominant, but from today's perspective it's very clear: they made some fundamental choices that didn't age well. As a result, DX on Windows is still not great, even if Visual Studio has the best features, and people with taste by and large prefer Linux.

Apple made an extremely strategic choice: rebuild the OS around BSD, which set them up to align with Linux (the language of servers). The question is: why? Go find out.

The difference is a matter of sensibility, and a matter of allowing that sensibility to exist and flourish in the business.

Re: Claude Code is being dumbed down?

#137

Post by co_king_3 »

knodi wrote: post #126
co_king_3 wrote: post #109

Earlier quoted context omitted.

I don't know about you, but I benefit so much from using Claude at work that I would gladly pay $80,000-$120,000 per year to keep using it.

What do you use it for, do you have example? For you to be ok with paying 80k to 120k I'm guessing its making you 375-450k a year?

I'm joking, my point is that it's already quite expensive and I don't think it's making anyone money.

Re: Claude Code is being dumbed down?

#138

Post by chairmanwow1 »

fooker wrote: post #100
lionkor wrote: post #79

Meanwhile GPT-5.3-Codex which just released recently is a huge change and much better. It now displays intermediate thinking summaries instead of being silent.

My experience using it from cursor has been fairly disappointing

Much better in the codex cli harness

Re: Claude Code is being dumbed down?

#139

Post by shevy-java »

This shows one problem here: a private entity controls Claude Code. You can reason that it brings benefits (perhaps), but to me it feels wrong to allow my thinking or writing code be controlled by a private entity. Perhaps I have been using Linux for too long - I may turn into RMS 2.0 (not really though, I like BSD/MIT licences too).

Re: Claude Code is being dumbed down?

#140

Post by thunfischtoast »

jtrn wrote: post #101

I find it hard to care about claims of degradation of quality, since this has been a firehouse of claims that don't map onto anything real and is extremely subjective. I myself made the claim in error. I think this is just as ripe for psychological analysis as anything else.

Did you read the article? It's not about subjective claims, it's about a very real feature getting removed (file reads showing the filepath and numbers of lines read).
Post reply on HN