Thread

1. onomojo · 1786044657 · focus · HN ↗

   Any benchmark showing Opus 5 as the best just loses credibility for me. Anyone who's actually used Opus 5 daily knows what I'm talking about.

   1. copperx · 1786044937 · focus · HN ↗

      I'm dumbfounded to see Opus 5 making SO MANY mistakes in coding simple stuff. Most times, Fable 5 comes out to be cheaper because it nails so many things much quicker than Opus 5.

      1. garciasn · 1786046393 · focus · HN ↗

         I have Fable plan and Opus implement. I haven't had any major issues working this way; however, Opus does seem plain fucking stupid compared to what I experienced with Sonnet previously.

         1. aenis · 1786046909 · focus · HN ↗

            I do the same, and generally have good results, but it does stupid things with gusto.

            I'd open a blog with "weird things Opus did". Today it launched a swarm of cpu-hogging processes to test if the widget showing machine and I/O load is rendering nicely and correctly. The test went fine, but it was no longer able to kill those processes since they were really effectively hogging the CPU in various ways - being diligent, some of them were hogging CPU, some were murdering the SSD, some were pounding on the network adapters. Took me 30 mins to recover the machine to a working state without killing the meaningful, messy, in-flight sessions i had going on on other projects.

         2. petesergeant · 1786047409 · focus · HN ↗

            > however, Opus does seem plain fucking stupid

            Infuriatingly so, in a way I don't remember Opus 4.8 being, but maybe I've just been ruined by Fable 5.

            1. hbn · 1786048486 · focus · HN ↗

               I bought my first LLM subscription with Claude right before they gave access to Fable 5.

               I got so used to it, when they finally pulled access for me and I had to go back to Opus I felt like I was working with my hands tied.

               I finally know what those women with AI boyfriends felt like when their app updated and it won't dirty talk with them anymore.

            2. moffkalast · 1786049833 · focus · HN ↗

               Fable has spoiled us all.

               1. sscaryterry · 1786056270 · focus · HN ↗

                  Not so sure, I'm sure Opus 5 is just shit.
      2. usef- · 1786047118 · focus · HN ↗

         Weird how different people's experiences are. If it's making simple mistakes something must be wrong in your setup/context I assume? It's been solid for me, beyond the usual LLMisms that all models have. But I keep context pretty minimal.

         1. cromka · 1786048157 · focus · HN ↗

            Statements like this typically come from working on the same setup and context using different models. I actually have that very experience now; I work on something security-adjacent so Fable often drops out, at which point Opus behaves like its lobotomized half-sibling. Pardon me the language, but I can't find a better example to be honest.
         2. nimonian · 1786048651 · focus · HN ↗

            Agreed. Opus 5 is doing just fine, slightly better than 4.8. It's personality is insufferable, but I find myself catching fewer problems at code review. It generally understands my conventions and isn't so eager to accrue tech debt.
         3. efficax · 1786052824 · focus · HN ↗

            Every model that comes out comes with a bunch of people saying "this one is actually dumb they were smart before" and I don't really get it. The models since Opus 4.5 have all been basically the same to me. Sometimes they do the wrong thing, so you have to steer and stop and correct them. Leaving them to operate on their own in no-human-in-the-loop harnesses often gets bad results. But if you single thread it, and keep your work targeted (you have to know what you want the thing to do!), clear your context, the models will do what you ask pretty reliably.
      3. TacticalCoder · 1786052592 · focus · HN ↗

         > I'm dumbfounded to see Opus 5 making SO MANY mistakes in coding simple stuff.

         To me it's not so much the dumb mistakes (although there are some of those) but the ultra-verbose, mega-inefficient "solutions" to some problems / prompts.

         Stuff that "works" if you're the kind of person that considers slamming a semi-trailer at 200 mph into a door did, technically, result in the door being somehow "open".

         As it's supposed to be one of the most advanced model, I can't help but wonder if the solutions are that bad/verbose/inefficient because we're already in a loop of models being trained on sloppy-pasta from previous models.

Unofficial Hacker News client; not affiliated with Y Combinator.