[kodablah]

That tweet says:

> Opus 5 can silently fallback to Opus 4.8 (without any notice) on the serverside if you hit a guardrail

But https://support.claude.com/en/articles/16049681-why-claude-s... says (emphasis mine):

> These checks cause Claude to _visibly_ fallback from Opus 5 to Opus 4.8 [...] You'll see a notice explaining that the model switched, and the response will be labeled with the model that answered.

So who is right? I know for Fable I am visibly told, is this tweet trying to say it is silent against what Anthropic is saying?

[solenoid0937]

Is some random guy on Twitter right, or official support docs that explicitly describe this scenario?

[pseudohadamard]

If it was Microsoft then definitely some random guy on Twitter.

For Anthropic, it's more a 50:50 toss-up.

[PunchyHamster]

Having a bit too much trust in AI companies have we ?

[SwellJoe]

So, announcing the fallback is better than doing it silently, but the fact that Fable falls back frequently for the kind of work I do (a lot of security oriented stuff lately, but it falls back on seemingly random stuff, sometimes, too), means I reach for it less. Getting interrupted mid-task makes it much less valuable. If I have any suspicion I'm going to hit the guardrails, I'll use something else.

[pseudohadamard]

Same problem here, I seem to hit guardrails all the time when doing code audits. Does anyone have any insight over whether they're less annoying in Opus 5 than Fable? That is, is it better to start with Opus 5 than Fable because you'll get kicked backed to Opus 4.8 less often?

There also seems to be some cross-pollination across models, going Fable, Fable, Fable, guardrail, Opus 4.8, Opus 4.8, ... gives more Fable-like results from Opus than just Opus 4.8, Opus 4.8, Opus 4.8, ...

[pseudohadamard]

Played with it for a couple of hours now, I'd say it's slightly better than Fable for coding and so far I haven't hit any guardrails while I'd hit them all the time with Fable.

[lossolo]

It's showing you're switched to 4.8, i just hit that while doing security research.

[trueno]

i wonder if anyone thinks im weird for still using 4.6 lmao it's my "good enough" model. im more than pleased at what i can whip up with 4.6, once local llm's get here with a decent sized context window and it feels like using 4.6, i shall depart the land of these dumb service subscriptions