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

721–730 of 732 posts

Re: Claude Code is being dumbed down?

#721

Post by subscribed »

ivanb wrote: post #562
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…

One thing this specific feature was letting me do is seeing when Claude Code takes a wrong turn, read a wrong memory MD file. I used to immediately interrupt and correct its course. Now it is more opaque and there is less of a hint at CC's reasoning.

And you burn more tokens. Works as intended I guess.

Re: Claude Code is being dumbed down?

#722

Post by espeed »

espeed wrote: post #678
dns_snek wrote: post #630

Earlier quoted context omitted.

That's approaching the problem from the worst possible angle. If your security depends on you catching 1 message in a sea of output and quickly rotating the credential everywhere before someone has a chance to abuse it then you were never secure to begin with. Not just because it requires constant attention which will eventually lapse, but because the agent has an unlimited number of ways to exfiltrate the key, for e…

I sent email to Anthropic (usersafety@anthropic.com, disclosure@anthropic.com) on January 8, 2025 alerting them to this issue: Claude Code Exploit: Claude Code Becomes an Unwitting Executor. If I hadn't seen Claude Code read my ssh file, I wouldn't have known the extent of the issue.

Correction: January 8, 2026

Re: Claude Code is being dumbed down?

#723

Post by elzbardico »

johndough wrote: post #719
elzbardico wrote: post #713

Earlier quoted context omitted.

Their price is not a signal of their costs, it is the result of competitive pressure. This shouldn't be so hard to understand. Companies have burned investor money for market share for quite some time in our world. This is the expected, the normal, why are you so defensive?

> why are you so defensive? Because you made stuff up, did not show any proof, and ignored my proof to the contrary. You made the claim: > Deepseek lies about costs systematically. DeepSeek broke down their cost in great detail, yet you simply called it "lies", but did not even mention which specific number of theirs you claim is a lie, so your statement is difficult to falsify. You also ignored my request for clarif…

You’re citing deepseek unaudited numbers. This is not even close to a proof. Unless proven otherwise it is propaganda. Meanwhile we have several industry experts pointing not only towards DeepSeek ridiculous claims of efficiency, but also the lies from other labs.

Re: Claude Code is being dumbed down?

#724

Post by johndough »

elzbardico wrote: post #723
johndough wrote: post #719

Earlier quoted context omitted.

> why are you so defensive? Because you made stuff up, did not show any proof, and ignored my proof to the contrary. You made the claim: > Deepseek lies about costs systematically. DeepSeek broke down their cost in great detail, yet you simply called it "lies", but did not even mention which specific number of theirs you claim is a lie, so your statement is difficult to falsify. You also ignored my request for clarif…

You’re citing deepseek unaudited numbers. This is not even close to a proof. Unless proven otherwise it is propaganda. Meanwhile we have several industry experts pointing not only towards DeepSeek ridiculous claims of efficiency, but also the lies from other labs.

Again, your claims are impossible to verify or falsify, because they are too unspecific.

> Meanwhile we have several industry experts pointing not only towards DeepSeek ridiculous claims of efficiency, but also the lies from other labs.

What are those "industry experts" saying that is made up and what is their basis for that?

> You’re citing deepseek unaudited numbers.

Which specific number are you claiming to be fake?

I could just guess blindly and find alternative sources for random numbers from DeepSeek's article.

For example, the tokens-per-second efficiency can also be calculated based on the 30k tps from this NVIDIA article: https://developer.nvidia.com/blog/nvidia-blackwell-delivers-...

But looking for other sources is a waste of my time, when you could just be more precise.

Re: Claude Code is being dumbed down?

#725

Post by alexandriaeden »

kissgyorgy wrote: post #14

This is why I am a big fan of self-hosting, owning your data and using your own Agent. pi is a really good example. You can have your own tooling and can switch any SOTA model in a single interface. Very nice! https://lucumr.pocoo.org/2026/1/31/pi/

This is exactly the right instinct. When you own the agent harness, you decide what's visible. I've been building my own tooling on top of Playwright for similar reasons — the feedback loop between 'what did the agent just do' and 'should I let it continue' is the core UX of any agent, not a detail to be abstracted away. Hiding it breaks the only trust mechanism the user has.

Re: Claude Code is being dumbed down?

#726

Post by nullbio »

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…

The solution was simple for me: Cancel my max sub, start using Codex instead. Hopefully others do the same and Anthropic will learn to listen to their users.

Re: Claude Code is being dumbed down?

#728

Post by yencabulator »

shepherdjerred wrote: post #534
ukuina wrote: post #95

Earlier quoted context omitted.

Patching's not long for this world; Claude Code has moved to binary releases. Soon, the NPM release will just be a thin wrapper around the binary.

the binary is just bun. I wrote this to inspect CC https://github.com/shepherdjerred/monorepo/tree/main/package...

Kinda crazy to buy a Javascript engine company to obfuscate your React TUI.

Re: Claude Code is being dumbed down?

#729

Post by shepherdjerred »

yencabulator wrote: post #728
shepherdjerred wrote: post #534

Earlier quoted context omitted.

the binary is just bun. I wrote this to inspect CC https://github.com/shepherdjerred/monorepo/tree/main/package...

Kinda crazy to buy a Javascript engine company to obfuscate your React TUI.

I doubt that's why they bought it. It's not obfuscated; just minified.

Re: Claude Code is being dumbed down?

#730

Post by puppymaster »

deaux wrote: post #518
puppymaster wrote: post #459

Earlier quoted context omitted.

interesting. they have been pretty receptive to my pull comments and discourse on issues. To each's anecdote I suppose.

https://github.com/anthropics/claude-code/issues/6235

yea so they dont want to include agents.md and that's perfectly fine with me.
Post reply on HN