kache#487
While Fable is an amazing model, don't get too excited: it is great, but still has the usual failure models of the other good LLMs we saw in the past, including GPT 5.5. If you look at Anthropic, Opus -> Fable was a huge jump. If you look at the field, GPT 5.5 -> Fable is incremental.
Positive users praise Fable for major gains in data analysis and personal use over GPT-5.5, while negative users dismiss the improvements as incremental PR stunts with the same failures and rising token costs.
@antirez I find Fable impressive but entirely non enjoyable. It feels like talking to gpt 5 pro. Non interactive and super slow. Probably for people who are running things without being in the loop this works.
I bet right now the maximum you can achieve in the field of software development is to use GPT 5.5 *and* Fable in a combination, cross-review cross-design style. The way I used Opus/GPT when they had similar performances a few months ago.
@mitsuhiko Yes basically it does not care about you writing while it works. Looks non-steerable in interactive way in the same way GPT 5.5 is. It's complicated to work like that, especially since right now models are not at a "work alone" level for many tasks.
@TechMDAI I believe the security thing is not a stunt. GPT 5.5 already uncovered tons of bugs and created a lot of issues in the security community.
@antirez IDK fable has been really wonderful for me, iterally making me rethink my decision of being an engineer lmao
@antirez I totally agree. Its very PR Stunt. The models is held back from the real work or is it really
@antirez they nerfed it though. it thinks everything i'm doing is cybersecurity and/or biology (even though it isn't) and falls back to opus 4.8. this is not really a new model release at all if you can't actually use it.
@antirez I don't think it's isolated at all, but I would bet that we have a k shaped community of people that steer vs people that loop. And the loopers are using more tokens :)
@antirez salvatore, una curiosità, che ne pensi dei modelli open, tipo deepseek v4 pro, rispetto a gpt e fable? Secondo te non sono abbastanza buoni? Per me, deepseek v4 pro funziona benissimo nella maggior parte dei casi (con il prompt/harness/setup giusto).
@antirez Do you think GTP 6 will be the next model ?
It literally told me something like this
"CLANG is not installed on this machine, so i am documenting this in PR body, can't fully test the output"
I was like wtf bro, there is clang installed, test properly and then open PR. It was like Ooooh yeah you are ABSOLUTELY RIGHT
So its same as any other model of clankers
@antirez @yacineMTB As someone who does Blockchain and security work, fable is the worst model of all time.
@antirez Do you think Deepseek could handle doing tasks delegated to it by plans created by 5.5/Fable? Ie, several tasks with documented outcomes/requirements.
@mitsuhiko Btw impressed by the fact that in the YouTube video I published today morning about Fable I lamented the non-steerability of the model and now you say this. So this must not be isolated feeling but most folks are facing this issue right now I bet.
@antirez @yacineMTB Hoping to have 5.6 soon enough so i don’t have uncancel my unthropic sub for a month
@antirez I think you need to do wider range of tasks before presuming 5.5 to fable is incremental. It most definitely is not.
@antirez Yeah, it’s still an LLM. Same rules still apply
e.g., what I wrote about here
@antirez Very early, but to me it feels significantly better at data analysis
@antirez Fair enough
@antirez more gpt shill
kache#487While Fable is an amazing model, don't get too excited: it is great, but still has the usual failure models of the other good LLMs we saw in the past, including GPT 5.5. If you look at Anthropic, Opus -> Fable was a huge jump. If you look at the field, GPT 5.5 -> Fable is incremental.