Hacker News Reader

Comment by hk__2 | Hacker News Reader

I’d argue the opposite. I’ve switched back and forth from one to the other and Opus/Fable has been constantly better than any GPT in my daily work. It’s a bit slower but it does the things right, with as little code as possible, some comments where needed. Codex is faster but you always have to correct it because it got something wrong; it writes tons of code ("let me add a small helper") with obvious comments.

View on HN

Purely anecdotally the one persistent issue I have with LLMs writing code is that they are absolutely paranoid and add a load of indirection and defensive crap and even if you prompt to avoid that it will often require manual steering to remove the cruft.

I have not noticed this with Opus 4.6+. The result is usually not too far from what I would have written myself.

Opus 4.6 was the best model in the family, following two ones were seriously brain damaged to do well on benchmarks.

yeah those have been horrible

I wouldn't say terrible-terrible but only better at from-prompt-to-solution rather than interactive discussing and problem solving.

I tend to define it "better at solving, worse at assisting phenomenon". Which doesn't properly show on benchmarks that only focus on the solving part.

I’ve experienced this with GPT but not with Opus/Fable.

I experience it with everything including opus/fable.

Though my feeling, no proof, is that the opus/fable today is not what it was months ago. there was a time for about a month where opus was incredible. Just incredible but as fable started to move out i swear to god it feels like sonnet now. Fable feels like opus used to but costs more.

recent gpts are horrendous for this, whereas recent claudes have a tic where they incessantly add useless comments referring to previous changes and will use multiple single-line comments instead of a standard multi-line docblock.

Sounds like my code. They may have been trained on my code!

The incessant need to constantly leave "the code doesn't work like <bad implementation>, it works like <good implementation>" frustrates me to no end. No amount of directions against it in project MEMORY, CLAUDE.md, or even embedded in the prompt seem to be able to stop it from doing this. I don't understand how it could have gotten into the training because I've legitimately never seen an actual person write code comments like this.

Maybe it's self trained. It eats its own output and likes it...

It writes code as if the audience is you, the user of Claude, and not other developers reading the code in the future. I found that it helped to instruct it to keep in mind who the audience is and only write comments that describe the current state of the code and never describe anything that can just be inferred from the git history. I found that that helped, and I almost never see these nonsense comments anymore.

Fallbacks and backward compatibility are killing me :) So many code paths that just don't fail predictably.

https://github.com/EspoTek/.claude/blob/master/CLAUDE.md

Stick the "Never suppress errors" section into your Claude.md, this will never happen again (works for me with Python/Flask, ymmv for other languages).

A lot of that sounds like offensive programming: https://en.wikipedia.org/wiki/Offensive_programming

Didn't know there was a word for that, thanks! Looks like my programming style matches my communication style in general. :P

I tell it to avoid belts and suspenders, don't leave dysfunctional code in, and fail loud. Seems to change that behavior.

Sounds like you are talking past each other. GP is saying the harness of codex is higher quality, which I can believe, even if the models are not as good as Opus/Fable.

GPT-5.5 is as good though, at least according to my personal experience and DeepSWE

yes, much faster, more token efficient and quality is also similar

i don't think so, i think it's 50% what work people are doing, 50% vibes. my experience with 5.5 is i like it more and get better results than 4.8/fable. which isn't to say i think it's a strictly better model, just been working better for me.

What do you mean "i don't think so"? What is it about the comment you are replying to that you don't think?

It's the other way actually. Cc is a better harness but gpt models are just so much better in my personal experience (at least for backend) ever since 5.4.

I really love the Opus/Fable models but I'm honestly sick to death of the buggy product. The CLI always has some weird issue. Right now it doesn't even output messages before tool calls, it just swallows them and they disappear.

I don't like OpenAI as a company, but they appear to have QA, and that is probably enough to get me to switch.

There was an issue on Claude Code the other day where it would only wait 60 seconds when it had asked a set of questions, then if it didn't get a response from the user it would just continue however it thought was best. Completely unusable. It took them nearly 48 hours to merge a fix.

That sounds intentional though.

Yes it was an intentionally added feature, that was extremely bad.

Glad I’m not the only one noticing this. It’s maddening.

Using remote control I will choose a model but Claude will always revert to Haiku for the first turn.

Basic stuff about features that are more than a week old just get no attention at all. From the outside Athropic seems to be a clear feature factory.

Same for me, that is why I switched to Pi. I still use Sonnet or Opus, but mainly GPT due to cost.

I'm not sure how meaningful this is. Fable only just recently become more broadly available, and GPT-5.6 is launching broadly today.

The comment I was responding to was talking about Codex usage in the past few months. This is a general feeling about Codex with Claude, not a model-to-model comparison.

A bit slower? I think for most of my tasks, Claude takes easily 2x longer for almost everything, even things like just analyzing code. It churns tons of tokens for quite simple things.

IMO that's exactly why it's a bit better at actual problem solving.

You absolutely do not "always have to correct" Codex. I'm not sure what you're doing, but I'd say 80-90% of its edits on my side it doesn't need any revisions.

> Codex is faster but you always have to correct it because it got something wrong

this has been my experience with Codex as well, and I have to fix its mistakes every single time. But recently, I literally threw away three hours of work because it kept adding hundreds of lines to my code base. When I restarted the entire work using Fable and Opus, it was like night and day.

I have both as well. I trust the output of Claude to a higher degree than what I get with Codex. I always have claude review codex output. That being said, I find gpt 5.5 more generically useful at a wider breadth of tasks. Straight coding though, it's no contest.

Obligatory YMMV, maybe your prompting style fits gpt better. We forget that this matters a lot

Reply on news.ycombinator.com