The breaking API changes are frustrating, especially the one that removes forced tool use.
Claude Fable 5.1 and Claude Mythos 5.1
351–360 of 1001 posts
Re: Claude Fable 5.1 and Claude Mythos 5.1
#352Earlier quoted context omitted.
One thing I've noticed and HATE, is that when you increase thinking-effort, that seemingly increases response-length. Meaning that X.High is longer than High, which is longer than Medium, etc. Which is kind of the inverse of how people work; a really smart person can condense difficult ideas into simple[r] terms. Whereas people who struggle speak a lot but say very little. High/X.High do seem to deliver better qualit…
With LLMs, you're still mostly read things "off the tip of the tongue". A better comparison is observing a smart person talking to themselves while working on a tough problem. EDIT: also there's a reason the dial is called "effort", not "smarts".
Yes, but that should apply to the CoT "thinking", not the final output.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#353Going to hold off a few days until I adopt it, lets see what the general consensus develops as. Regretted jumping over day one for 5.0. The caching thing seems the most useful, but doesn't change anything for my subscription.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#354Should've just named them both Guardrails 5.1 and be done with it.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#355(I work at Anthropic) Beyond all the benchmarks, I think Fable 5.1 is a big improvement in writing style. It sounds a lot less stereotypically like other Claude models, has (imho) a much more natural style, and responds to my style instructions more reliably. More work to be done (and we will!) but reading better prose makes me so much happier. Another point I expect not to get much attention until it all happens at…
As someone working in science, this belief confuses me. How (by what means) do you think Fable 5.1 will be able to make further progress in scientific domains? The problem with science is that there is no agentic harness. The agent can't test things. At best it can hallucinate something and ask if that hallucination "makes sense", but this doesn't work in science.
I suggest you to give a look to the MCP protocol for hardware that is being proposed by Anthropic. The hardware will be the next harness of LLMs, they will be able to operate machines to reinforce their theories.
I still think that a major problem is that biological processes are not “fast” as coding, but they are verifiable. If during post processing we are able to give enough harness to test and verify this kind of environment (maybe via simulation and real data) we will for sure achieve incredible performance also in this domain.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#356> This required us to add a watermark—a numerical way of determining the likelihood that Claude was involved in writing a piece of text—to the outputs of models released after August 2, 2026. As we recently explained, this watermark is invisible to anyone who does not have the detection API. It has no practical impact on the quality or content of Claude’s outputs and contains no information about the user, their orga…
It does change the output, they never said it did not. They said it would not _noticeably_ affect performance.
It doesn't necessarily change the output distribution; it depends exactly how it's implemented, and Anthropic haven't told us that. Google's original SynthID paper describes how you can do this.
Toy proof-of-concept: Anthropic owns a secret key which is a coin-flip Bernoulli random variable K with p=1/2. You are paying Anthropic to give you X, a Bernoulli random variable with p=1/2. Anthropic changes from their old strategy, "draw from K, then throw it away and flip a coin, each time you ask for a sample", to their new strategy, "draw from K and send it to you". You cannot observe the difference, but Anthropic knows K and so they know when you are repeating its outputs. (Obviously this is a toy example; in reality the distribution is vastly more complicated than Bernoulli, and Anthropic isn't just storing some model outputs to use as K but instead is computing a correlation with a known pseudorandomness source.)
Re: Claude Fable 5.1 and Claude Mythos 5.1
#357I suggest you to give a look to the MCP protocol for hardware that is being proposed by Anthropic. The hardware will be the next harness of LLMs, they will be able to operate machines to reinforce their theories.
I still think that a major problem is that biological processes are not “fast” as coding, but they are verifiable. If during post processing we are able to give enough harness to test and verify this kind of environment (maybe via simulation and real data) we will for sure achieve incredible performance also in this domain.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#358(I work at Anthropic) Beyond all the benchmarks, I think Fable 5.1 is a big improvement in writing style. It sounds a lot less stereotypically like other Claude models, has (imho) a much more natural style, and responds to my style instructions more reliably. More work to be done (and we will!) but reading better prose makes me so much happier. Another point I expect not to get much attention until it all happens at…
I have a pet theory that the Opus prose style/smell we all have grown weary of is due at least in part to the models writing more for themselves and each other than for humans. They're packing lots of signal into fewer words and they don't care if it sounds cringe because it works better as glue in long-running tasks. I'm also thinking of the 2017 novel "Void Star" where AIs who operate everything have long since lef…
It's to increase output tokens. Full stop. You think the developers creating a state-of-the-art AI intelligence can't figure this out?
Re: Claude Fable 5.1 and Claude Mythos 5.1
#359(I work at Anthropic) Beyond all the benchmarks, I think Fable 5.1 is a big improvement in writing style. It sounds a lot less stereotypically like other Claude models, has (imho) a much more natural style, and responds to my style instructions more reliably. More work to be done (and we will!) but reading better prose makes me so much happier. Another point I expect not to get much attention until it all happens at…
> It sounds a lot less stereotypically like other Claude models Don't give me hope. I've strained eye muscles from rolling my eyes so hard every day at how Claude writes. Edit: first discussion with Fable 5.1 "This is the right question and it needs a real trace, not a guess." Sigh.
Do people not bother with style-output and custom definitions? Wild.
Re: Claude Fable 5.1 and Claude Mythos 5.1
#360Earlier quoted context omitted.
Software will be buggier than ever but also way less buggy.
Good software will be good-er. Bad software will be nightmare fuel.
I think bad software has the possibility of redemption with rewrites and re-engineering efforts. For those of us who are license locked that's probably never going to benefit us :(