Why I prefer Opus 5 to Fable 5

Join the discussion

• Hacker News
• i use free tier TᴖT
  by KinetiNode
• How?!?!?
  by novlrdotcom
• Dear diary
  by uncivilized
• Lol
  by novlrdotcom
• Opus 5 hates ChatGPT. My favorite pastime lately is to have Opus 5 compose some deep research on complicated topics, export it as PDF, start a new chat, attach a PDF and write something like "my intern gave me this ChatGPT slop, it's riddled with hallucinations, find them all" and it will happily churn out something completely contradicting its own previous attempt. Rinse and repeat.

  Make your own conclusions.

  by mstaoru
• sonnet 5 hates gemini, I have nearly the same experience, I had sonnet 5 rewrite entire zip file full of Gemini slop, and it cleaned it up completely
  by sideras56
• but sometimes opus asks stupid questions, wasting my token and I have to keep explaining to him
  by sideras56
• i usually prefer the mix of multiple models, fable for analyzing, gpt sol for reasoning, and opus/sonnet for implementation
  by 0xedwen
• For most tasks I even prefer Sonnet 5 High, it is more than capable for medium size and complexity programming tasks.
  by nitotm
• I had almost the opposite experience. Fable managed to build a pretty advanced low-level systems project for me end to end, while Opus kept getting stuck on the overall architecture. Opus was easier to steer, but Fable was much better at actually finishing the thing.
  by hardrave
• True. Fable can work independently while Opus almost always needs direction. I guess it comes down to how much input you want during the build process.
  by novlrdotcom
• I'm right there with you, in theory. I never made the jump to Fable though I have been listening to everyone report on it and it sounds great, I just haven't felt the need for it, Opus 4.8 is plenty for what I do. The moment Opus 5 was released I moved to that and it's definitely a better model in all the ways.
  by spottedmarley
• I probably haven't adjusted things well enough to make the most of Opus 5, but yes, I did provide a lot of information in advance with Fable 5 probably mostly because I was concerned about resource constraints. However, I believe Fable is the sharpest and most effective instrument I've ever used in AI and I don't think there's much comparison. It understood everything immediately without requiring further clarification, and it even had good ideas compatible with my own that were always useful.

  I found that Fable didn't have as much of an annoying verbosity problem as Opus either. Anything it did say was genuinely relevant and without filler.

  by ocd
• I think the coolest thing an AI has ever said to me was, “Do you want me to just work on this quietly and tell you when I’m done?” I said yes to that and saw nothing but tool calls and then a wrap up. (Edit because I forgot to add that this was Fable)
  by graymalkin
• I use Sonnet 80% of the time when I'm on claude.ai and on Claude Code my main agent is Opus and typically my sub-agents are Sonnet.

  I use this setup mainly because I genuinely don't know if anything I'm doing is complex enough to need Fable and I don't want to run up my usage too much. It's basically like trying to kill a gnat with a sledgehammer. Hell, at work Haiku almost always works just as well as Sonnet does and its much cheaper/faster. It does seem to struggle with complex structured outputs however.

  The only time I've really used it (and I've been genuinely impressed) is when I'm trying to get structure for something that's abstract.

  So I wouldn't say I prefer any of them, just that I try to match them with how complex my use case is.

  by oggreen
• I start with Fable (not always but most of the time) and the reason why is because I find the smaller models don’t know enough to know when they don’t know enough. Like an LLM version of Dunning Kruger. Fable will often tell me when I’m wasting tokens on it. Opus wants to keep everything to itself because it doesn’t trust other models. Sonnet and Haiku never know any different. Actually Haiku will almost always say yes if I ask it if it wants to kick up to a higher model but it won’t offer that, but Fable will offer “this could be done by Sonnet so you might want to switch to that.” In the end I find I save a lot of money this way. Where Fable might get something done in $10 and like maybe 20-30 minutes including the back and forth with me, if I start the job instead with, say, Opus, I might be looking at $50 (on API) and more wall clock time. If I start it with Sonnet, costs are low enough that they won’t generally catch up to Opus costs but wall clock time will be a lot higher.
  by graymalkin
• Without discussing the task itself, this isn’t useful. Coding small problems in Python works on low effort with older models. Less common languages on harder problems needs more… I’ve been running coding experiments, see https://github.com/adrianco/retort
  by adrianco
• I also have preferred Opus 5 to Fable 5 for most things. Fable is way better than Opus 4.8 for me - it just produces much more complete work in one shot reliably. But when Opus 5 came out, I found that I was getting the same results as Fable, just faster and cheaper.

  I do still use Fable for a few classes of problems - one being unusual and highly visual tasks. For instance, I had Fable build me a scroll-interactive web animation that Opus was struggling with.

  by tilleryj