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

391–400 of 732 posts

Re: Claude Code is being dumbed down?

#391

Post by gigatexal »

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…

Boris! Unrelated but thank you and the Anthropic team for Claude code. It’s awesome. I use it every day. No complaints. You all just keep shipping useful little UX things all the time. It must be because it’s being dogfooded internally. Kudos again to the team!

Re: Claude Code is being dumbed down?

#392

Post by cdelsolar »

co_king_3 wrote: post #170
kadushka wrote: post #162

Earlier quoted context omitted.

I would probably pay $2000 a month if I had to - it's a small fraction of my salary, and the productivity boost is worth it.

It's *worth it* when you're salaried? Compared to investing the money? Do you plan to land a very-high-paying executive role years down the line? Are you already extremely highly paid? Did Claude legitimately 10x your productivity? edit: Fuck I'm getting trolled

I don't know why you keep insisting that no one is making any money off of this. Claude Code has made me outrageously more productive. Time = Money right?

Re: Claude Code is being dumbed down?

#394

Post by latchkey »

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…

This is an insanely good response. History, backstory, we screwed up, what we're doing to fix it. Keep up the great work!

Re: Claude Code is being dumbed down?

#395

Post by gchamonlive »

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…

So in a nutshell Claude becoming smarter means that logic that once resided in the agent is being moved to the model?

If that's the case, it's important to asses wether it'll be consistent when operating on a higher level, less dependent on the software layer that governs the agent. Otherwise it'll risk Claude also becoming more erratic.

Re: Claude Code is being dumbed down?

#396

Post by teaearlgraycold »

falcor84 wrote: post #378
oldestofsports wrote: post #350

Earlier quoted context omitted.

You dont expose error details to the user for security reasons, even though it does indeed make the user experience worse.

I understand not exposing a full stack trace, but I don't see any excuse to not even expose a googleable error code. If me having an error code makes your product insecure, then you have a much bigger problem.

I show the stack trace on AGPL projects. Why hide what they can already see for themselves?

Re: Claude Code is being dumbed down?

#397

Post by latchkey »

cactusplant7374 wrote: post #390
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…

In what terminals is rendering slow? I really think GPU acceleration for terminals (as seen in Ghostty) is silly. It's a terminal. Edit: I can't post anymore today apparently because of dang. If you post a comment about a bad terminal at least tell us about the rendering issues.

As someone who's business is run through a terminal, not everyone uses ghostty, even though they should. Remember, that they don't have a windows version.

Re: Claude Code is being dumbed down?

#398

Post by sdoering »

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…

There are so many config options. Most I still need to truly deeply understand.

But this one isn't? I'd call myself a professional. I use with tons of files across a wide range of projects and types of work.

To me file paths were an important aspect of understanding context of the work and of the context CC was gaining.

Now? It feels like running on a foggy street, never sure when the corner will come and I'll hit a fence or house.

Why not introduce a toggle? I'd happily add that to my alisases.

Edit: I forgot. I don't need better subagent output. Or even less output whrn watching thinking traces. I am happy to have full verbosity. There are cases where it's an important aspect.

Re: Claude Code is being dumbed down?

#399

Post by bcherny »

cactusplant7374 wrote: post #390
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…

In what terminals is rendering slow? I really think GPU acceleration for terminals (as seen in Ghostty) is silly. It's a terminal. Edit: I can't post anymore today apparently because of dang. If you post a comment about a bad terminal at least tell us about the rendering issues.

VSCode (xterm.js) is one of the worst, but there's a large long tail of slow terminals out there.

Re: Claude Code is being dumbed down?

#400

Post by steinnes »

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 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 the author that verbose mode isn’t the answer. Seems to me this should be configurable
Post reply on HN