Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Codex logging bug may write TBs to local SSDs

github.com

Post reply on HN
Print view View original

171–180 of 296 posts

Re: Codex logging bug may write TBs to local SSDs

#171

Post by geodel »

hombre_fatal wrote: post #95
r_lee wrote: post #64

Earlier quoted context omitted.

if we are at 10x with AI and near AGI or ASI, then how is it possible that these products (Codex, Claude Code CLI) are still such garbage? shouldn't this "agentic AI revolution" have long solved this already? no way they're over there saying "we are on it plz wait" or that "it's too much effort"?

Like anything, you have to decide between polish vs switch to any other task in the queue. If you choose too much from the latter, then polish suffers, yet that's a human thing. Also, Codex and Claude Code aren't as bad as people say. I think most of the noise is embellished by the "hah see? AI sucks" angle. It's kind of like how HNers would claim to your face that you can't actually build anything with Javascript an…

> yet that's a human thing.

is this joke?

Here we are talking about trillon dollar AI companies who claim AI can fix decade old bugs and create new compilers, OSs and what not. Are parallel agents working autonomously to fix issues as well as create new features not allowed at these companies?

Re: Codex logging bug may write TBs to local SSDs

#172

Post by hombre_fatal »

coldtea wrote: post #125
hombre_fatal wrote: post #95

Earlier quoted context omitted.

Like anything, you have to decide between polish vs switch to any other task in the queue. If you choose too much from the latter, then polish suffers, yet that's a human thing. Also, Codex and Claude Code aren't as bad as people say. I think most of the noise is embellished by the "hah see? AI sucks" angle. It's kind of like how HNers would claim to your face that you can't actually build anything with Javascript an…

> Like anything, you have to decide between polish vs switch to any other task in the queue Why do you "have to decide"? Let some agents go at both of those, isn't that what they claim people can just do? > Also, Codex and Claude Code aren't as bad as people say. I think most of the noise is embellished by the "hah see? AI sucks" angle. Why shouldn't it? They're not the ones making the extraordinary claims.

> Why do you "have to decide"? Let some agents go at both of those, isn't that what they claim people can just do?

Because your code is still marching somewhere in tokens per second. You have to decide where they are allocated: polish or the next thing. Humans still are the ones prompting LLMs and deciding what is done.

> isn't that what they claim? Why shouldn't it? They're not the ones making the extraordinary claims.

Even if I grant that someone else makes excessive claims, why would that let you off the hook to stay grounded?

Though I don't grant it. Maybe if Anthropic claimed that Opus makes all decisions at the company and builds all software without humans doing all the prompting, the critics would make more sense.

Until then, it looks more like a double standard: if software built with AI has any issues, then see, AI is shit and the humans who invoked it had no role in it. e.g. it could be the case that Anthropic's Claude Code engineers just aren't doing as much polish as they should.

Better answer: Someone asked why might it be the case that AI-written software has issues, and it has a real answer. Marketing claims are a different conversation.

Re: Codex logging bug may write TBs to local SSDs

#173

Post by redox99 »

christophilus wrote: post #112

Well, everyone's bashing on OpenAI as well they should, but just a reminder, unlike Claude Code, Codex is officially available to customize here: https://github.com/openai/codex It's fairly easy to patch.

That's the CLI, not the codex app which is proprietary.

Re: Codex logging bug may write TBs to local SSDs

#174

Post by sambcui »

jofzar wrote: post #41
b--l wrote: post #10

Codex is one of the most infamous examples of slopware. Just having the window unhidden on my mac will cause it to use 100% of the GPU displaying the spinner message. THE SPINNER MESSAGE CAUSES 100% GPU USAGE ON AN MBP M5!! So any time you're waiting on the model (which is 90% of the time), your fans will be blasting (careful, don't use it on battery). The issue is on github and close to 6 months old. Probably since…

> Codex is one of the most infamous examples of slopware Woah, let's not forget Claude code is right there

I don’t know if you can resonate, but I feel like the Vibe Coded codex and Claude Code desktop apps are iterating way faster than they should be.

Re: Codex logging bug may write TBs to local SSDs

#175

Post by malfist »

sambcui wrote: post #174
jofzar wrote: post #41

Earlier quoted context omitted.

> Codex is one of the most infamous examples of slopware Woah, let's not forget Claude code is right there

I don’t know if you can resonate, but I feel like the Vibe Coded codex and Claude Code desktop apps are iterating way faster than they should be.

How are they iterating? I've not noticed anything major changing between the versions of my claude code. Other than that sometimes this version includes /btw and sometimes it's missing.

Re: Codex logging bug may write TBs to local SSDs

#176

Post by espdev »

Imustaskforhelp wrote: post #5

I don't understand how Codex can blunder so badly. I imagine that even if they would be using vibe-coding, surely they must have some good engineers. So why is there such severe bugs? One can argue that these products are the flagship products of their respective AI companies aside from the AI models themselves of course. I imagine that this story will be picked up by the news left and right, some stories just feel t…

> I don't understand how Codex can blunder so badly. I imagine that even if they would be using vibe-coding, surely they must have some good engineers. So why is there such severe bugs?

I'd say this is also partly a problem of working under intense pressure and the demand to work faster and faster - even faster now with "AI". All these companies are competing with each other very aggressively and are driving their employees like horses in order to win the "AI" race.

Re: Codex logging bug may write TBs to local SSDs

#177

Post by hombre_fatal »

geodel wrote: post #171
hombre_fatal wrote: post #95

Earlier quoted context omitted.

Like anything, you have to decide between polish vs switch to any other task in the queue. If you choose too much from the latter, then polish suffers, yet that's a human thing. Also, Codex and Claude Code aren't as bad as people say. I think most of the noise is embellished by the "hah see? AI sucks" angle. It's kind of like how HNers would claim to your face that you can't actually build anything with Javascript an…

> yet that's a human thing. is this joke? Here we are talking about trillon dollar AI companies who claim AI can fix decade old bugs and create new compilers, OSs and what not. Are parallel agents working autonomously to fix issues as well as create new features not allowed at these companies?

Humans still decide what LLMs do in a code base, full stop.

Re: Codex logging bug may write TBs to local SSDs

#178

Post by bandrami »

me551ah wrote: post #122
jofzar wrote: post #41

Earlier quoted context omitted.

> Codex is one of the most infamous examples of slopware Woah, let's not forget Claude code is right there

Claude is also weird for being the only coding assistant that for some reason doesn't support AGENTS.md. Codex, Amp, Cursor all of them support it and read from it, but not claude which forces it's users to use CLAUDE.md instead. The issue is the higest voted issue on their gitlab repo: https://github.com/anthropics/claude-code/issues/6235

So there's this amazing thing called a symlink

Re: Codex logging bug may write TBs to local SSDs

#179

Post by geodel »

hombre_fatal wrote: post #172
coldtea wrote: post #125

Earlier quoted context omitted.

> Like anything, you have to decide between polish vs switch to any other task in the queue Why do you "have to decide"? Let some agents go at both of those, isn't that what they claim people can just do? > Also, Codex and Claude Code aren't as bad as people say. I think most of the noise is embellished by the "hah see? AI sucks" angle. Why shouldn't it? They're not the ones making the extraordinary claims.

> Why do you "have to decide"? Let some agents go at both of those, isn't that what they claim people can just do? Because your code is still marching somewhere in tokens per second. You have to decide where they are allocated: polish or the next thing. Humans still are the ones prompting LLMs and deciding what is done. > isn't that what they claim? Why shouldn't it? They're not the ones making the extraordinary clai…

> Maybe if Anthropic claimed that you could write an unsupervised loop that writes perfect software, the critics would make more sense.

Or to be upstanding, ethical companies that they are. Just put disclaimer after every prompt response and on their website "AI generated code has no absolutely no guarantee of quality or correctness. Human prompter must be held accountable for any mistake or inaccuracies."

Hope it wouldn't be too much bother to these important companies.

Re: Codex logging bug may write TBs to local SSDs

#180

Post by thewebguyd »

r_lee wrote: post #64
b--l wrote: post #10

Codex is one of the most infamous examples of slopware. Just having the window unhidden on my mac will cause it to use 100% of the GPU displaying the spinner message. THE SPINNER MESSAGE CAUSES 100% GPU USAGE ON AN MBP M5!! So any time you're waiting on the model (which is 90% of the time), your fans will be blasting (careful, don't use it on battery). The issue is on github and close to 6 months old. Probably since…

if we are at 10x with AI and near AGI or ASI, then how is it possible that these products (Codex, Claude Code CLI) are still such garbage? shouldn't this "agentic AI revolution" have long solved this already? no way they're over there saying "we are on it plz wait" or that "it's too much effort"?

> shouldn't this "agentic AI revolution" have long solved this already?

Daily reminder that Anthropic took over a year to fix the Claude Code terminal flickering issue despite proclaiming all over the internet that software development as a "solved problem."

Apple forked over $250 Million in a class action over false advertising for Apple Intelligence. When do we start seeing the same for the misleading and outright false claims coming out of the frontier labs about the model capabilities? At this point the marketing is doing more harm than the technology itself because its warping the perceptions of those at the top that make decisions. The only reason tokenmaxxing was ever a thing was because marketing mislead execs and technology decisions were made based on vibes instead of evidence.

Post reply on HN