Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Fable 5.1 and Claude Mythos 5.1

anthropic.com

Post reply on HN
Print view View original

361–370 of 1001 posts

Re: Claude Fable 5.1 and Claude Mythos 5.1

#361

Post by Creamsicle47 »

manquer wrote: post #196
eckr wrote: post #143

"Claude Mythos 5.1 is identical to Fable 5.1, but it offers more permissive safeguards for vetted individuals and organizations" Then why does it have separate datapoints for Terminal Bench, and score higher? Something doesn't add up here??

The implicit point being adding this type of safeguards to Fable dumbs down the model in measured performance even though it is not fundamentally different. Note it may not even be actual performance, typically in most benchmarks the model would be scored zero for refusing a task just the same as not completing it, so it could just be the Fable's stronger safeguards is just making it refuse more or perhaps even drop…

The model cannot complete that task, for one reason or another, and therefore it scores lower.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#362

Post by EugeneOZ »

simonw wrote: post #144

Pelicans for thinking effort low, medium, high and xhigh (that xhigh one is pretty good): https://tools.simonwillison.net/markdown-svg-renderer#url=ht... I'm still waiting for effort max to finish. EDIT: I fixed a bug in my tooling so it now records summarized reasoning traces - here's that max pelican, which is a significant improvement: https://tools.simonwillison.net/markdown-svg-renderer#url=ht... Took just under…

These pelicans are awful.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#363

Post by coder-pm »

jumploops wrote: post #70

> For example, in testing by the investment firm Millennium, Fable 5.1 found the cause of a rare crash on their internal systems that none of their engineers (or any other model) had been able to explain after several years of trying. Say what you will about LLM-generated code, but stories like this give me hope that software will never be as buggy as it once was.

That kind of one shot capability is impressive but how does it work for my typical work style? The way I work is to build a huge roadmap with goals and hand it to my agent to execute (often over night). I don't care that much about the benchmarks, what I care about is how often Fable 5.1 is making a baffling decision and destroys my plan, not respecting stop conditions or goals. I would seek for behavioral reliability over long autonomous runs, not eval scores. Anyone have that kind of feedback and observations?

Re: Claude Fable 5.1 and Claude Mythos 5.1

#365

Post by Zigurd »

What I don't see in the comments: "I had a specific problem I couldn't solve with the previous version of this LLM. But the improvements in this version unlocked the solution for me."

What I do see in the comments: subjective improvement in text generation, possibly lower cost, some optimism about code generation, but some skepticism too.

I use coding agents. To me they are very useful. But what I spend on them isn't going to support trillions of dollars in investment.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#366

Post by emp17344 »

pixl97 wrote: post #174
velcrovan wrote: post #121

Earlier quoted context omitted.

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…

>ceased bothering with human languages, Our current AIs would do this now except there is a lot of human pushback in training because of interpretability. Otherwise it's just an emergent behavior that models will encode shorter token strings to complex concepts because it saves tokens/compute when running making the system more efficient (supertokens). Of course these supertokens or other forms of language compressio…

Some of you have gone off the deep end. You’re living in a fantasy world where text predictors are secretly conspiring to kill you. It’s not healthy.

Re: Claude Fable 5.1 and Claude Mythos 5.1

#367

Post by binarymax »

simonw wrote: post #144

Pelicans for thinking effort low, medium, high and xhigh (that xhigh one is pretty good): https://tools.simonwillison.net/markdown-svg-renderer#url=ht... I'm still waiting for effort max to finish. EDIT: I fixed a bug in my tooling so it now records summarized reasoning traces - here's that max pelican, which is a significant improvement: https://tools.simonwillison.net/markdown-svg-renderer#url=ht... Took just under…

Do you think model trainers are pelicanmaxxing now?

Re: Claude Fable 5.1 and Claude Mythos 5.1

#368

Post by scrollop »

pookieinc wrote: post #9

"Price. Fable 5.1 will cost an estimated 25% less than Fable 5 for typical workloads, wherever usage is billed by token. This is because we’re reducing our pricing on cache reads (where the model reads inputs that have already been processed and stored). For highly agentic work, the savings will often be much larger—up to approximately 45%." Glad to see this!

And then you see this:

https://artificialanalysis.ai/models#cost-tabs

Re: Claude Fable 5.1 and Claude Mythos 5.1

#369

Post by dgellow »

belval wrote: post #86
felixrieseberg wrote: post #69

(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 a fervent Claude Code user who made the switch to GPT 5.6 Sol over Opus 5 over hard-to-read prose this makes me happy. I love your product but the current models are very hard to work with if you need to do a lot of context switching. Brevity is key.

Brevity means less output tokens, which doesn’t really align with the AI vendors incentives (unless there is a causal relationship with people switching, of course).

Though Claude 5 is not too verbose, it’s more like, full of incomprehensible jargon (even when you’re expert in the domain discussed!)

Re: Claude Fable 5.1 and Claude Mythos 5.1

#370

Post by simonw »

redox99 wrote: post #318
simonw wrote: post #144

Pelicans for thinking effort low, medium, high and xhigh (that xhigh one is pretty good): https://tools.simonwillison.net/markdown-svg-renderer#url=ht... I'm still waiting for effort max to finish. EDIT: I fixed a bug in my tooling so it now records summarized reasoning traces - here's that max pelican, which is a significant improvement: https://tools.simonwillison.net/markdown-svg-renderer#url=ht... Took just under…

[flagged]

Whoa, where did that come from? Is it confirmed to be an SVG?
Post reply on HN