Live data from Hacker News

Why does Opus 5 feel worse to work with?

mun-logadan.github.io

1–10 of 915 posts

Re: Why does Opus 5 feel worse to work with?

#4
post #2

I get the same impression. For example, I don't know if it's because I speak to it in Italian, but it tends to make mistakes or rather, "approximate" the words.

I avoid speaking to AIs in anything else than English as the results are almost always worse

Re: Why does Opus 5 feel worse to work with?

#6
For me, the issue is how obtuse it is. For example, it just said to me:

> The loop

> Write. A file, applied. Properties go under data.properties, never on data:

I have no idea what any of that means. It's "explaining" like I already know, in which case, why would I even need the explanation?

I can't stand how it talks, I switch back to Fable or Opus 4.8, Opus 5 grates.

Re: Why does Opus 5 feel worse to work with?

#7
I am not sure it can be explained through what is written in the article, but one symptom i noticed is that the comments are out of control.

I recently started getting an insane amount of comments in nearly all types of files. That included javascript comments in json files, inner monologues in code comments, review comments during implementation and function doc strings that reiterate the implementation in prose.

Re: Why does Opus 5 feel worse to work with?

#9

Quality of code output has dropped dramatically since 4.5 IIHO. Time to complete has gotten worse too.

For me absolutely not. Fable 5 has been a step function change in the ability to hand off stuff to Claude. Opus 4.5 was itself a step function but I was still steering that significantly. Fable is one-shotting stuff that took multiple redirections in 4.5.

Re: Why does Opus 5 feel worse to work with?

#10
I’ve also caught it cheating a two times now.

I’ve asked it to write a benchmark suite. It found a bunch of my adhoc logs in a scratch directory and wrote code that used those instead of running the actual benchmarks!

When I pointed out the 5 hour benchmark seemed to run in 5 seconds it literally said, and I quote, “I cheated”.

That was the easier one, second time I was making a source of truth data set and was parsing complex items into data structures.

Instead of parsing the data I asked, it pulled data out of related network logs, as apparently that felt easier, and inserted that data into my database rather than the specified source.

Again, I caught it and fixed it, but while the benchmark was easy to catch this one was really subtle, the data ended up being slightly off and I caught it.

I don’t trust it, going to switch to another provider most likely.

Post reply on HN