[flagged]
crashed when I clicked play campaign
Try picking a map from the map picker up on the top left drop down section, then click g-23 and you'll be matched against bots.
Fable 5 is Back
81–90 of 438 posts
Re: Fable 5 is Back
#82> When Claude Fable 5 declines a request, the Messages API returns stop_reason: "refusal" as a successful HTTP 200 response, not an error This is precisely what comes to mind when I think “successful”.
A missed opportunity to use the HTTP 451 status code. https://en.wikipedia.org/wiki/HTTP_451
5 years ago, we may have expected that robots would write APIs that utilized every HTTP code, what we got was a json with a stringified error field..
Re: Fable 5 is Back
#83> There's an issue with the selected model (claude-fable-5[1m]). It may not exist or you may not have access to it. Run /model to pick a different model.
Re: Fable 5 is Back
#84I really hope they reconsider adding Fable access back to the subscription plans, at least the 20x plan. I know it was the original intention when the 14 day (I think) time frame was originally announced, and they were working to keep it on subscription plans. But no word if thats even a thing anymore?
The market will force them to bring it back. They're probably capacity constrained right now, or need to figure out whether they need another pricing tier for it to "fit in a subscription". What they don't want is for someone to code for 4 days of the week and cap out every week.
Re: Fable 5 is Back
#85The loss of trust in using US based model's is unlikely to come back though. Anthropic with it's hyped doomsday messaging, and the administration falling for it (at best), has eroded a lot of trust and has triggered an arms race of sorts.
If you've built a product based on AI, then diversify or make an abstraction layer so your product is model agnostic and you can plug and play any model. If you're an end user like a software engineer, just use another model or like Gemini or ChatGPT. That is more productive than complaining about a trust which wasn't there in the first place to begin with.
Anthropic provides a service and they can stop offering it regardless of export ban or not, same goes for any other AI company in any country. If you really wants a trusted LLM, then run your own open weight model.
Re: Fable 5 is Back
#86It won't even review a cyber security blog post I wrote. Absolutely worthless and pitiful guardrails.
Re: Fable 5 is Back
#87Happy to see that Fable is back, was sad to see it go after getting to use it for only 1.5 days before. Add on top sonnet 5 availability and coding is looking fine again.
Re: Fable 5 is Back
#88Maybe, for some projects, instead of generating code with it, it would be useful to generate a plan and the loop(tests/formal verification),because those take much less tokens than a full project, and than use the loop using the older models ?
this is the idea of opusplan https://code.claude.com/docs/en/model-config#opusplan-model-...
Article has a section about context window size settings
I love not getting compacted so often, but 1M context is trash right now, the degradation in speed and quality is too great above ~600k context
Not different than what everyone knows, but the 1M context is masqueraded as an innovation the same way 64k context used to be to 8k context
Re: Fable 5 is Back
#89Earlier quoted context omitted.
Right, but originally they announced a period of time it was included in plans, and then they were "working hard" to extend the period and eventually make it a permanent fixture of the plans.
I'd imagine they want to do price segmentation. Sell the best model for $50k a year to corporations willing to pay full price, keep the rest of us on a lower tier. Gotta pay for that infra somehow.
I just don't really understand the entire strategy behind this. Or their horrible, horrible communication.
Because right now it's as if Fable/Mythos 5 is "the end of the line". It's as if this is the best their models are ever going to be. So what the hell are we going to get next? All of their models will forever inch closer to Fable, but never reach it? That doesn't make any sense.
It all seems so dramatic. Instead of just saying honestly "Look, this model is a beast to run, but we're striving to reach the same quality in a cheaper model down the line" all we get is "Oh my god, it's so big and scary, and it costs so much to run, woe is me!"
Re: Fable 5 is Back
#90I'll be using it tonight but grudgingly so. Grudgingly because after July 7th, I'm not going to all of a sudden, start paying API prices (and maybe that's the problem) when I'm used to a subscription that gives me multiples in comparative value. Perhaps this is the fabled "token economics will come for everyone this year" that I've been reading about? In any case, I'll use the hell out of it to extract as much as I c…
[flagged]